Select a calendar:
Filter November Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for the 3rd week of November
-
2022 Women in Technology Intern and Analyst Conference (External Event)
Sun, Nov 13, 2022
Viterbi School of Engineering Career Connections
Workshops & Infosessions
The Wells Fargo Women in Technology Intern/Analyst Conference is an exclusive two-day program designed to encourage and inspire women who have an interest in pursuing a career in Technology. A select group of high-performing students from diverse backgrounds will be invited to participate.
During this conference, you will have the opportunity to learn from successful women in technology at Wells Fargo who will share their expertise and knowledge to help you become a future leader. You will develop an understanding of Wells Fargos unique values and culture, which you will experience first-hand in your interactions with highly talented team members. You will have an accelerated opportunity to interview with hiring managers for intern/analyst program positions across the Wells Fargo Technology platform.
Conference Activities
Consideration for Openings in the 2023 Intern/Analyst Program
Panel Discussions with Alumni from the Technology Program
Professional Development Workshop
Networking with Technology Leaders and Program Alumni
Presentation about Wells Fargo, Technology, and Career Paths
Location: Charlotte, North Carolina
Wells Fargo will pay all travel and lodging expenses for selected participants.
The conference is open to all students who are currently pursuing a bachelors degree in a STEM related major (examples: Computer Science and Computer Engineering) and graduating between December 2022-June 2025.
2022 Women in Technology Intern and Analyst Conference
Invitation and attendance at the conference does not guarantee an intern/analyst position placement. Interviews for the various 2023 openings will take place during the conference on the 2nd day.
Wells Fargo will only consider candidates who are presently authorized to work for any employer in the United States and who will not require work visa sponsorship from Wells Fargo now or in the future in order to retain their authorization to work in the United States.
External employer-hosted events and activities are not affiliated with the USC Viterbi Career Connections Office. They are posted on Viterbi Career Connections because they may be of interest to members of the Viterbi community. Inclusion of any activity does not indicate USC sponsorship or endorsement of that activity or event. It is the participants responsibility to apply due diligence, exercise caution when participating, and report concerns to vcareers@usc.eduAudiences: Everyone Is Invited
Contact: RTH 218 Viterbi Career Connections
-
PhD Thesis Proposal - Ali Alotaibi
Tue, Nov 15, 2022 @ 08:00 AM - 10:00 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Candidate: Ali Alotaibi
Title: Automated Repair of Layout Accessibility Issues in Mobile Applications
Time: Tuesday, November 15, 8:00 AM-10:00 AM PST
Committee: William GJ Halfond (chair), Murali Annavaram, Nenad Medvidovic, Mukund Raghothaman, and Chao Wang.
Abstract:
An increasing number of people are now dependent on mobile devices to access data and complete essential tasks. For people with disabilities, mobile apps that violate accessibility guidelines can prevent them from carrying out these activities. Layout accessibility issues are among the top accessibility issues in mobile applications. These issues impact the accessibility of mobile apps and make them difficult to use, especially for older people and people with disabilities. Unfortunately, existing techniques are limited in helping developers debug these issues. These techniques are only capable of detecting the issues. Therefore, the repair of layout accessibility issues remains a manual process.
Automated repair of layout accessibility issues is complicated by several challenges. First, a repair must account for multiple issues holistically in order to preserve the relative consistency of the original app design. Second, due to the complex relationship between UI components, there is no clear way of identifying the set of elements and properties that needs to be modified for a given issue. Third, assuming the relevant views and properties can be identified, the number of possible changes that need to be considered grows exponentially as more elements and properties need to be considered. Finally,
a change in one element can create cascading changes that lead to further problems in other areas of the UI. Together, these challenges make a seemingly simple repair difficult to achieve. In this thesis proposal, I propose an automated framework for repairing layout accessibility issues in mobile applications.
Zoom Link: https://usc.zoom.us/j/98863735277?pwd=MTVITkNqY2dQdmhKWWRkRElWeVppUT09
WebCast Link: https://usc.zoom.us/j/98863735277?pwd=MTVITkNqY2dQdmhKWWRkRElWeVppUT09
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
-
Healthcare Labor ManagementTue, Nov 15, 2022 @ 11:00 AM - 12:00 PM
Executive Education
Conferences, Lectures, & Seminars
Speaker: TBD, TBD
Talk Title: Healthcare Labor Management
Abstract: The USC Viterbi School of Engineering's Healthcare Labor Management course offered in partnership with the Institute of Industrial and Systems Engineers (IISE) will provide an understanding and overview of critical aspects of designing and executing a comprehensive labor management program.
Host: Executive Education
More Info: https://viterbiexeced.usc.edu/healthcare-labor-management-course-page/
Audiences: Registered Attendees
Contact: Corporate and Professional Programs
Event Link: https://viterbiexeced.usc.edu/healthcare-labor-management-course-page/
-
PhD Defense - Aaron Chan
Tue, Nov 15, 2022 @ 03:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Candidate: Aaron Chan
Title: Generating and Utilizing Machine Explanations for Trustworthy NLP
Time: Tuesday, November 15, 3:00PM-5:00PM PST
Committee: Xiang Ren (chair), Robin Jia, Jesse Thomason, Bistra Dilkina, Morteza Dehghani
Abstract:
Neural language models (LMs) have yielded remarkable success on a wide range of natural language processing (NLP) tasks. However, LMs sometimes exhibit undesirable behavior, which can be difficult to resolve due to LMs' opaque reasoning processes. This lack of transparency poses serious concerns about LMs' trustworthiness in high-stakes decision-making, thus motivating the use of machine explanations to automatically interpret how LMs make their predictions. In my thesis, I argue that building human trust in NLP systems requires being able to: (A) generate machine explanations for LM behavior faithfully and plausibly and (B) utilize machine explanations to improve LM generalization and decision-making. First, to address (A), I propose UNIREX, a unified learning framework for jointly optimizing machine explanations with respect to both faithfulness and plausibility, without compromising the LM's task performance. Second, for (B), I introduce ER-Test, a framework for evaluating the out-of-distribution generalization ability of LMs that are regularized via strongly-supervised machine explanations. Third, to further support (B), I present SalKG, an algorithm for improving LM generalization by regularizing LMs via weakly-supervised machine explanations. Finally, I discuss several future directions for achieving (A) and (B).
Zoom Link: https://usc.zoom.us/j/95606515253?pwd=QzBvaVVpcWtYSFhVYzVoUi9tdHBRdz09
WebCast Link: : https://usc.zoom.us/j/95606515253?pwd=QzBvaVVpcWtYSFhVYzVoUi9tdHBRdz09
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
-
Photonics seminar speaker - Jeffrey Moses, Tuesday, November 15th at 3pm in MCB 102
Tue, Nov 15, 2022 @ 03:00 PM - 04:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Jeffrey Moses, Cornell University
Talk Title: Tackling longstanding challenges in ultrafast nonlinear optics via foreign but familiar physics
Series: Photonics Seminar Series
Abstract: Silicon-Optical nonlinearities have expanded the optics and photonics toolset for applications as diverse as high intensity laser science, quantum information processing, and the imaging and spectroscopy of biological systems. Key to many applications is use of the nonlinear polarizability of materials to couple photons between optical fields, giving rise to amplification and frequency conversion methods that expand the reach of lasers and other photon sources, both classical and non-classical. Other applications use light 'self-effects' to guide, switch, and modulate. However, optical nonlinearities are often small, and even when large enough, the spatiotemporal and spectral inhomogeneities in nonlinear optical systems can severely hamper the efficiency and bandwidth of power flow between waves.
Our group has been seeking ways to 'trick' nonlinear systems into modes of evolution that can avoid the normal limiting behaviors or to make use of unconventional nonlinear interactions. I'll discuss a few of these that possess familiar physics that are somewhat foreign to optical light pulses, such as rapid adiabatic passage in optical frequency conversion, oscillation damping in parametric (i.e., lossless) wave mixing, and nonlinear optical interactions involving coherent phonon coupling. And I will present some technologies that they can enable, including efficient parametric amplifiers, dispersion-free octave-spanning frequency up- and down-converters, strong cross-phase modulation, and the removal of spectral distinguishability.
Biography: Jeff Moses joined the faculty at Cornell University in 2014, where he leads the Ultrafast Phenomena and Technologies Group in the School of Applied and Engineering Physics. He received his B.S. from Yale and Ph.D. from Cornell, with both degrees in applied physics, and spent several years at the Optics & Quantum Electronics Group in the Research Laboratory of Electronics at MIT as a postdoctoral associate and research scientist. He has received the US National Science Foundation CAREER award and was an Air Force Office of Scientific Research Young Investigator.
Host: Mercedeh Khajavikhan, Michelle Povinelli, Constantine Sideris; Hossein Hashemi; Wade Hsu; Mengjie Yu; Wei Wu; Tony Levi; Alan E. Willner; Andrea Martin Armani
More Information: Jeffery Moses Flyer.pdf
Location: Michelson Center for Convergent Bioscience (MCB) - 102
Audiences: Everyone Is Invited
Contact: Marilyn Poplawski
-
Epstein Institute - ISE 651 Seminar
Tue, Nov 15, 2022 @ 03:30 PM - 04:50 PM
Daniel J. Epstein Department of Industrial and Systems Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Robert Hildebrand, Assistant Professor, Grado Dept. of Industrial & Systems Engineering, Virginia Tech
Talk Title: Redistricting, Gerrymandering, and Mixed Integer Nonlinear Programming
Host: Prof. Suvrajeet Sen
More Information: November 15, 2022.pdf
Location: Ethel Percy Andrus Gerontology Center (GER) - GER 206
Audiences: Everyone Is Invited
Contact: Grace Owh
-
MFD Seminar With Professor Lily Cheung
Tue, Nov 15, 2022 @ 04:00 PM - 05:20 PM
Mork Family Department of Chemical Engineering and Materials Science
Conferences, Lectures, & Seminars
Speaker: Professor Lily Cheung, Assistant Professor, School of Chemical and Biomolecular Engineering, Georgia Institute of Technology
Talk Title: MFD Seminar With Professor Lily Cheung
Biography: Research Interests:
-Engineering of genetically encoded biosensors
-Quantitative fluorescence microscopy and image analysis
-Computational models of gene regulatory networks
-Transcriptional regulation and developmental biology of plants
The goal of the Cheung lab is to bring quantitative techniques and mathematical modeling to plants in order to gain systems-level insight into their physiology and development, particularly to understand how metabolic and gene regulatory networks interact to control homeostasis and growth.
Host: Professor Finley, Mork Family Department of Chemical Engineering and Materials Science
Location: James H. Zumberge Hall Of Science (ZHS) - 352
Audiences: Everyone Is Invited
Contact: Anthony Tritto
-
Boeing Information Session - Production and Industrial Engineering Careers (Viterbi, On-Campus)
Tue, Nov 15, 2022 @ 06:00 PM - 07:00 PM
Viterbi School of Engineering Career Connections
Workshops & Infosessions
Production and Industrial Engineering Careers
Date: Tuesday, November 15
Time: 6:00 p.m. - 7:00 p.m.
Location: Ronald Tutor Hall (RTH) 211
Register on Viterbi Career Gateway
An inclusive workplace built around ideas, respect and innovation â” that is what you will find here. Join us and help build the future.
Attend this event to learn about production and industrial engineering careers at the world's largest aerospace manufacturer.
All majors and class levels are welcome to attend. Boeing is hiring for internships and full-time positions.
Boeing attendees will include:
Kevin Stigerts: Chief Engineer, BCA Equipment & Tool Engineering
Everly Manzana: Industrial Engineer, BCA Supplier Management Operations
Mike Beazer: Sr. Manager, Production & Industrial engineering
Mark Webb: Director, Production Profitability
What majors and class levels are you interested in connecting with? All
Can you offer Visa sponsorship? Are you able to hire a student on CPT or OPT? NoLocation: 211
Audiences: Everyone Is Invited
Contact: RTH 218 Viterbi Career Connections
-
Healthcare Labor Management
Wed, Nov 16, 2022 @ 11:00 AM - 12:00 PM
Executive Education
Conferences, Lectures, & Seminars
Speaker: TBD, TBD
Talk Title: Healthcare Labor Management
Abstract: The USC Viterbi School of Engineering's Healthcare Labor Management course offered in partnership with the Institute of Industrial and Systems Engineers (IISE) will provide an understanding and overview of critical aspects of designing and executing a comprehensive labor management program.
Host: Executive Education
More Info: https://viterbiexeced.usc.edu/healthcare-labor-management-course-page/
Audiences: Registered Attendees
Contact: Corporate and Professional Programs
Event Link: https://viterbiexeced.usc.edu/healthcare-labor-management-course-page/
-
DEN@Viterbi: How to Apply Virtual Info Session
Wed, Nov 16, 2022 @ 11:00 AM - 12:00 PM
DEN@Viterbi, Viterbi School of Engineering Graduate Admission
Workshops & Infosessions
Join USC Viterbi representatives for a step-by-step guide and tips for how to apply for formal admission into a Master's degree or Graduate Certificate program. The session is intended for individuals who wish to pursue a graduate degree program completely online via USC Viterbi's flexible online DEN@Viterbi delivery method.
Attendees will have the opportunity to connect directly with USC Viterbi representatives and ask questions about the admission process throughout the session.
Register Now!WebCast Link: https://uscviterbi.webex.com/uscviterbi/onstage/g.php?MTID=ecd2626ed617b316b446484a4ed9c56f0
Audiences: Everyone Is Invited
Contact: Corporate & Professional Programs
-
Center of Autonomy and AI, Center for Cyber-Physical Systems and the Internet of Things, and Ming Hsieh Institute Seminar Series
Wed, Nov 16, 2022 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Hayk Martiros, Skydio
Talk Title: Frontiers of Autonomous Flight and Real-Time 3D Reconstruction
Series: Center for Cyber-Physical Systems and Internet of Things
Abstract: At Skydio, we ship autonomous robots that are flown at scale in unknown environments every day by our customers to capture incredible video, automate dangerous inspections, build digital twins, and protect the lives of soldiers and first responders. These robots operate intelligently and make decisions at high speed using their onboard cameras and algorithms. We've invested a decade of R&D into handling complex visual scenarios and building a robust pipeline for visual navigation, obstacle avoidance, and rapid trajectory planning. On top of that, we're building a rich ecosystem of real-time 3D reconstruction technology to enable 360 global localization and map building on our drones.
During the talk, I will discuss the technology and impact of our core navigation stack and 3D Scan technology, and what research frontiers lie ahead. I plan to share visual examples of the algorithms in action, and connect to how these products solve pressing global challenges and enable next-generation operations across multiple industries. I will also introduce SymForce, our library for fast symbolic computation, code generation, and nonlinear optimization. This library powers many of our algorithms, and we have just published and open-sourced it as a contribution to the robotics community.
Biography: Hayk is a roboticist leading the autonomy group at Skydio, building robust visual autonomy to enable the positive impact of drones. Hayk has worked at Skydio since 2015 and was one of its first employees, where he contributed to all of Skydio's core autonomy systems. He now focuses on technical management of world-class engineers and researchers. Hayk's technical interests are in computer vision, deep learning, nonlinear optimization, systems architecture, and symbolic computation. His previous works include novel hexapedal robots, collaboration between robot arms, micro-robot factories, solar panel farms, and self-balancing motorcycles. Hayk was born in Yerevan, Armenia and grew up in Fairbanks, Alaska. He did his undergraduate study at Princeton University and graduate study at Stanford University.
Host: Somil Bansal, somilban@usc.edu
Webcast: https://usc.zoom.us/webinar/register/WN_ySGInGwKRKKHX7NHJwTk3QLocation: Online
WebCast Link: https://usc.zoom.us/webinar/register/WN_ySGInGwKRKKHX7NHJwTk3Q
Audiences: Everyone Is Invited
Contact: Talyia Whtie
-
PhD Defense - Aleksei Petrenko
Wed, Nov 16, 2022 @ 03:00 PM - 04:30 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Candidate: Aleksei Petrenko
Thesis title: High-Throughput Methods for Simulation and Deep Reinforcement Learning
Committee members: Gaurav S. Sukhatme (chair), Stefanos Nikolaidis, Jesse Thomason, Mike Zyda, and Rahul Jain
Location: RTH 306
Date: November 16. 2022
Time: 3 pm
Zoom link: https://usc.zoom.us/j/8712894950
Thesis abstract:
Advances in computing hardware and machine learning have enabled a data-driven approach to robotic autonomy where control policies are learned from raw data via interactive experience collection and learning. In this thesis we discuss a specific implementation of this approach: we show how control policies can be trained in simulated environments using model-free deep reinforcement learning techniques and then be deployed on real robotic systems.
We build towards this vision by developing tools for efficient simulation and learning under a constrained computational budget. We improve systems design of reinforcement learning algorithms and simulators to create high-throughput GPU-accelerated infrastructure for rapid experimentation. We then apply these systems and algorithms to continuous control problems in challenging domains. We first consider the problem of quadrotor swarm coordination. By scaling up training in a CPU-based flight simulator we train robust policies that are able to control physical quadrotors flying in tight formations. We then use large batch reinforcement learning in a massively parallel physics simulator IsaacGym to learn dexterous object manipulation with a multi-fingered robotic hand and we transfer these skills from simulation to reality using automatic domain randomization.
The high-throughput learning infrastructure developed for these and other projects is released as an open-source codebase "Sample Factory 2.0" to facilitate and accelerate further progress in the field.
Location: Ronald Tutor Hall of Engineering (RTH) - 306
WebCast Link: https://usc.zoom.us/j/8712894950
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
-
AME Seminar
Wed, Nov 16, 2022 @ 03:30 PM - 04:30 PM
Aerospace and Mechanical Engineering
Conferences, Lectures, & Seminars
Speaker: Khalid Jawed, UCLA
Talk Title: Reduced Order Modeling and Inverse Design of Flexible Structures by Machine Learning
Abstract: Recent advances in highly deformable structures necessitate simulation tools that can capture nonlinear geometry and nonlinear material. We propose machine learning, neural networks (NN) in particular, to capture this nonlinearity and solve highly nonlinear inverse problems in structural mechanics. Two representative problems will be discussed in this talk.
In the first problem, we use NN to reduce the number of variables and speed up the simulation by orders of magnitude. As a test case, we explore the dynamical simulation of a slinky, a pre-compressed elastic helix that is widely used as a toy for children. However, most often the deformation of a slinky can be fully captured by the deformation of its helix axis. Instead of simulating the entire helical structure, the axis of the helix is a reduced-order representation of this system. We use NN to store the elastic forces of the slinky in its reduced-order representation, utilizing the concept of neural ordinary differential equations. The NN is trained using data from a fine-grained 3D rod simulation called the Discrete Elastic Rods (DER). Once the elastic forces in the reduced representation are stored in the NN, force balance equations can be solved in this representation for the dynamic simulation. This results in savings in computational time without much impact on its physical accuracy.
In the second problem, we explore shape-morphing structures that spontaneously transition from planar to 3D shapes. This is a transformative technology with broad applications in soft robotics and deployable systems. However, realizing these morphing structures that can achieve certain target shapes is challenging and typically involves a painstaking process of trials and errors with complex local fabrication and actuation. We propose a rapid design approach for fully soft structures that can achieve targeted 3D shapes through a fabrication process that happens entirely on a 2D plane. By combining the strain mismatch between layers in a composite shell and locally relieving stress by creating kirigami cuts, we are able to create 3D free buckling shapes from planar fabrication. However, the large design space of the kirigami cuts and strain mismatch presents a challenging task of inverse form finding. We develop a symmetry-constrained active learning approach to learn how to explore the large design space strategically. Interestingly, we report that, given a target 3D shape, multiple design solutions exist, and our physics-guided machine learning approach can find them in a few hundred iterations. Desktop-controlled experiments and finite element simulations are in good agreement in examples ranging from peanuts to flowers.
Acknowledgment: Our lab is supported by the National Science Foundation (Award numbers: IIS-1925360, CMMI-2053971, CMMI-2101751, CAREER-2047663, OAC-2209782, CNS-2213839), the National Institute of Food and Agriculture of the US Department of Agriculture (Award # 2021-67022-34200, 2022-67022-37021), and the Department of Energy (Smart Manufacturing Institute, UCLA).
Biography: M. Khalid Jawed is an Assistant Professor in the Department of Mechanical and Aerospace Engineering of the University of California, Los Angeles, and the Principal Investigator of the Structures-Computer Interaction Laboratory. He received his Ph.D. and Master's degrees in Mechanical Engineering from the Massachusetts Institute of Technology in 2016 and 2014, respectively. He holds dual Bachelor's degrees in Aerospace Engineering and Engineering Physics from the University of Michigan, Ann Arbor. He also served as a Postdoctoral Researcher at Carnegie Mellon University. He received the NSF CAREER Award in 2021, the outstanding teaching award from UCLA in 2019, the outstanding teaching assistant award from MIT in 2015, and the GSNP best speaker award at the American Physical Society March Meeting in 2014.
Dr. Jaweds research interests lie at the intersection of structural mechanics and robotics, emphasizing a data-driven and artificially intelligent approach to the modeling and design of programmable smart structures. Current research projects include robotic manipulation of flexible structures, numerical simulation of highly deformable structures, soft robotics, and robotics for precision agriculture.
Host: AME Department
More Info: https://ame.usc.edu/seminars/
Webcast: https://usc.zoom.us/j/98775609685?pwd=a2lSd01oY0o2KzA4VWphbGxjWk5Qdz09Location: Seaver Science Library (SSL) - 202
WebCast Link: https://usc.zoom.us/j/98775609685?pwd=a2lSd01oY0o2KzA4VWphbGxjWk5Qdz09
Audiences: Everyone Is Invited
Contact: Tessa Yao
Event Link: https://ame.usc.edu/seminars/
-
ServiceNow Open House (Virtual, External)
Thu, Nov 17, 2022 @ 10:00 AM - 11:00 PM
Viterbi School of Engineering Career Connections
Workshops & Infosessions
At ServiceNow, our technology makes the world work for everyone, and our people make it possible. Our diverse team is changing the world with products that make a meaningful impact on people and communities. The more of 'you' you bring to work, the better. When you join ServiceNow, the world works.
Who is ServiceNow?
ServiceNow creates digital experiences that help organizations work smarter, faster, and better. Our purpose is to make the world work better for everyone.
ServiceNow Open Houses:
We are excited to announce our new Open Houses this Fall! These Open Houses are
available to anyone that would like to learn more about ServiceNow, our culture, and opportunities. Each open house will consist of an info session about ServiceNow and breakout rooms with recruiters and ServiceNow professionals. Join us and do not miss out on all the fun!
ServiceNow Workshops:
We are excited to announce that we are bringing back our career development
workshop series. These are free, virtual, career development workshops aimed to help those looking to jumpstart their careers in the tech industry. We'll be covering valuable topics that you won't want to miss!
ServiceNow Virtual Events
- Open House September 7th | 10 to 11 am
- Stand Out at Career Fairs and Conferences
Workshop September 14th| 10 to 11 am
- Open House September 22nd | 10 to 11 am
- Open House October 5th | 10 to 11 am
- Build Your Personal Brand and Give Your LinkedIn a Makeover Workshop October 12th |10 to 11 am
- Open House October 20th | 10 to 11 am
- Open House November 2nd |10 to 11 am
- How to Ace your In-Person and Virtual Interview Workshop November 9th 10:00 AM to 11:00 AM PDT
- Open House November 17th |10 to 11 am
- Open House November 30th | 10 to 11 am
- Overcoming Imposter Syndrome Workshop December 14th | 10 to 11 am
- Open House December 15th | 10:00 to 11:00 am
Check out all of our events and RSVP HERE
External employer-hosted events and activities are not affiliated with the USC Viterbi Career Connections Office. They are posted on Viterbi Career Connections because they may be of interest to members of the Viterbi community. Inclusion of any activity does not indicate USC sponsorship or endorsement of that activity or event. It is the participants responsibility to apply due diligence, exercise caution when participating, and report concerns to vcareers@usc.edu
Location: online
Audiences: Everyone Is Invited
Contact: RTH 218 Viterbi Career Connections
-
Machine Learning Center Seminar: Yang Liu (UC Santa Cruz) - Agency Bias in Machine Learning
Thu, Nov 17, 2022 @ 10:00 AM - 11:30 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Yang Liu, UC Santa Cruz
Talk Title: Agency Bias in Machine Learning
Series: Machine Learning Seminar Series
Abstract: A trained machine learning model (e.g., a classifier) will ultimately observe data generated according to agents' responses. For instance, the rising literature on strategic classification concerns the setting where agents are fully rational and can best respond to a classifier in their own interests. The above interaction will lead to a distribution shift between training and deployment and will challenge the existing performance and fairness guarantees of the trained model. In this talk, I'll discuss three types of agency bias that arise due to the above interactional effects between agents and machine learning models. I'll then go over possible mitigation efforts, including our very recent works on certifying the fairness guarantees on an unknown and possibly different deployment distribution.
References:
[1] Unfairness Despite Awareness: Group-Fair Classification with Strategic Agents. Andrew Estornell, Sanmay Das, Yang Liu and Yevgeniy Vorobeychik. Preprint, 2022.
[2] Actionable Recourse in Linear Classification. Berk Ustun, Alexander Spangher and Yang Liu
ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT), 2019.
[3] Unintended Selection: Persistent Qualification Rate Disparities and Interventions. Reilly Raab and Yang Liu. Neural Information Processing Systems (NeurIPS), 2021.
[4] Fairness Transferability Subject to Bounded Distribution Shift. Yatong Chen, Reilly Raab, Jialu Wang and Yang Liu. Neural Information Processing Systems (NeurIPS), 2022.
Prof. Liu will give his talk in person at EEB 248 and we will also host the talk over Zoom.
Register in advance for this webinar at:
https://usc.zoom.us/webinar/register/WN_WtHgpFUFSbCI214E2i9q3Q
After registering, attendees will receive a confirmation email containing information about joining the webinar.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Yang Liu is currently an Assistant Professor of Computer Science and Engineering at UC Santa Cruz (2018 - present). He was previously a postdoctoral fellow at Harvard University (2016 - 2018). He obtained his Ph.D. degree from the Department of EECS, University of Michigan, Ann Arbor in 2015. He is interested in weakly supervised learning and algorithmic fairness. He is a recipient of the NSF CAREER Award and the NSF Fairness in AI award (lead PI). He has been selected to participate in several high-profile projects, including DARPA SCORE and IARPA HFC. His recent works have won four best paper awards at relevant workshops.
Host: Yan Liu
Webcast: https://usc.zoom.us/webinar/register/WN_WtHgpFUFSbCI214E2i9q3QLocation: Hughes Aircraft Electrical Engineering Center (EEB) - 248
WebCast Link: https://usc.zoom.us/webinar/register/WN_WtHgpFUFSbCI214E2i9q3Q
Audiences: Everyone Is Invited
Contact: Department of Computer Science
-
NL Seminar -Pragmatic Interpretability
Thu, Nov 17, 2022 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Shi Feng, Univ of Illinois, Chicago
Talk Title: Pragmatic Interpretability
Series: NL Seminar
Abstract: Abstract: REMINDER
Meeting hosts only admit guests that they know to the Zoom meeting. Hence, you are highly encouraged to use your USC account to sign into Zoom.
If you are an outside visitor, please inform us at nlg DASH seminar DASH host AT isi DOT edu beforehand so we will be aware of your attendance and let you in.
In person attendance will be permitted for USC ISI faculty, staff, students only. Open to the public virtually via the zoom link and online.
Machine learning models have been quite successful at emulating human intelligence but their potential as intelligence augmentation is less explored. Part of the challenge is our lack of understanding in how these models work, and this is the problem interpretability is trying to tackle. But most existing interpretability work takes models trained under the emulation paradigm and adds humans into the mix post-hoc-the human's role is largely an afterthought. In this talk, I advocate for a more pragmatic approach to interpretability and emphasize modeling the human's needs in their cooperation with AIs. In the first part, I discuss how the human-AI team can be evaluated and optimized as a unified decision-maker, and how the model can learn to explain selectively. In the second part, I discuss how human intuition measured outside of the working with an AI context can be incorporated into models and explanations. I'll conclude with a brief discussion on formulating the model's pragmatic inference about its human teammate.
Biography: Shi Feng is a postdoc at University of Chicago working with Chenhao Tan. He got his PhD from University of Maryland under Jordan Boyd-Graber. He is interested in human-AI cooperation: how machine learning can help humans make better decisions, and how humans can provide supervision more effectively. His past work focuses on natural language processing, and covers topics including interpretability, adversarial attacks, robustness, and human-in-the-loop evaluations.
Host: Jon May and Meryem Mhamdi
More Info: https://nlg.isi.edu/nl-seminar/
Webcast: https://www.youtube.com/watch?v=C8jUO4w5xwULocation: Information Science Institute (ISI) - Virtual and ISI-Conf Rm#689
WebCast Link: https://www.youtube.com/watch?v=C8jUO4w5xwU
Audiences: Everyone Is Invited
Contact: Pete Zamar
Event Link: https://nlg.isi.edu/nl-seminar/
-
DEN@Viterbi - 'Limited Status: How to Get Started' Virtual Info Session
Thu, Nov 17, 2022 @ 05:00 PM - 06:00 PM
DEN@Viterbi, Viterbi School of Engineering Graduate Admission
Workshops & Infosessions
Join USC Viterbi for our upcoming Limited Status: How to Get Started Virtual Information Session via WebEx to learn about the Limited Status enrollment option. The Limited Status enrollment option allows individuals with an undergraduate degree in engineering or related field, with a 3.0 GPA or above to take courses before applying for formal admission into a Viterbi graduate degree program.
USC Viterbi representatives will provide a step-by-step guide for how to get started as a Limited Status student and enroll in courses online via DEN@Viterbi as early as the Spring 2023 semester.
Register Now!WebCast Link: https://uscviterbi.webex.com/uscviterbi/onstage/g.php?MTID=e5de607b5583e1aab441954360e7719de
Audiences: Everyone Is Invited
Contact: Corporate & Professional Programs
-
Viterbi Career Connections Workshop
Thu, Nov 17, 2022 @ 05:00 PM - 06:00 PM
USC Viterbi School of Engineering
Workshops & Infosessions
Join us for a workshop to learn about the Viterbi Career Connections office resources, resume, networking, and job/internship search.
Location: Sign into EngageSC to View Location
Audiences:
Contact: Noe Mora
Event Link: https://engage.usc.edu/viterbi/rsvp?id=387578
-
WIE x Viterbi Impact: Resume/Career Skills Workshop
Thu, Nov 17, 2022 @ 05:00 PM - 06:00 PM
Viterbi School of Engineering Student Affairs
Workshops & Infosessions
Join WIE and the Viterbi Career Center at their resume and career skills workshop where they will give students the skills necessary to conduct themselves at a professional setting. Food will be provided!!!
Location: Sign into EngageSC to View Location
Audiences:
Contact: Maia Calderon-Ramos
Event Link: https://engage.usc.edu/WIE/rsvp?id=387687
-
DEN@Viterbi - 'Limited Status: How to Get Started' Virtual Info Session
Fri, Nov 18, 2022 @ 11:00 AM - 12:00 PM
DEN@Viterbi, Viterbi School of Engineering Graduate Admission
Workshops & Infosessions
Join USC Viterbi for our upcoming Limited Status: How to Get Started Virtual Information Session via WebEx to learn about the Limited Status enrollment option. The Limited Status enrollment option allows individuals with an undergraduate degree in engineering or related field, with a 3.0 GPA or above to take courses before applying for formal admission into a Viterbi graduate degree program.
USC Viterbi representatives will provide a step-by-step guide for how to get started as a Limited Status student and enroll in courses online via DEN@Viterbi as early as the Spring 2023 semester.
Register Now!WebCast Link: https://uscviterbi.webex.com/uscviterbi/onstage/g.php?MTID=e21c9e9c52fa44bd72f923ea7aadbff75
Audiences: Everyone Is Invited
Contact: Corporate & Professional Programs
-
The EiS Communications Hub's Three Minute Thesis Contest for Ph.D. Students
Fri, Nov 18, 2022 @ 12:00 PM - 01:30 PM
Viterbi School of Engineering Student Affairs
Workshops & Infosessions
The EiS Communications Hub presents USC Viterbi's first Three Minute Thesis contest!
An 80,000-word thesis would take 9 hours to present, but in this contest, Ph.D. students will present their research in just 3 minutes with just one slide.
Join us and support Ph.D. students as they share their work! Vote for your favorite speaker as the "people's choice!"
Questions? Contact eishub@usc.edu.
Location: Ronald Tutor Hall of Engineering (RTH) - 115
Audiences: Everyone Is Invited
Contact: Helen Choi
-
ECE Seminar: Learning Efficiently in Data-Scarce Regimes
Fri, Nov 18, 2022 @ 01:00 PM - 02:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Mohammad Rostami, Research Assistant Professor, Dept of CS / Research Lead, USC-ISI
Talk Title: Learning Efficiently in Data-Scarce Regimes
Abstract: The unprecedented processing demand, posed by the explosion of big data, challenges researchers to design efficient and adaptive machine learning algorithms that do not require persistent retraining and avoid learning redundant information. Inspired from learning techniques of intelligent biological agents, identifying transferable knowledge across learning problems has been a significant research focus to improve machine learning algorithms. In this talk, we explain how the challenges of knowledge transfer can be addressed through embedding spaces that capture and store hierarchical knowledge.
We first focus on the problem of cross-domain knowledge transfer. We explore the problem of zero-shot image classification, where the goal is to identify images from unseen classes using semantic descriptions of these classes. We train two coupled dictionaries that align visual and semantic domains via an intermediate embedding space. We then extend this idea by training deep networks that match data distributions of two visual domains in a shared cross-domain embedding space.
We then investigate the problem of cross-task knowledge transfer in sequential learning settings. Here, the goal is to identify relations and similarities of multiple machine learning tasks to improve performance across the tasks. We first address the problem of zero-shot learning in a lifelong machine learning setting, where the goal is to learn tasks with no data using high-level task descriptions. Our idea is to relate high-level task descriptors to the optimal task parameters through an embedding space. We then develop a method to overcome the problem of catastrophic forgetting within a continual learning setting of deep neural networks by enforcing the tasks to share the same distribution in the embedding space.
Finally, we focus on current research directions to expand past progress and plans for future research directions. Through this talk, we demonstrate that despite major differences, problems within the above learning scenarios can be tackled using a unifying strategy that allows transferring knowledge effectively.
Biography: Mohammad Rostami is a research assistant professor at the USC CS department and a research lead at the USC Information Sciences Institute. He received Ph.D. degree in Electrical and Systems Engineering from the University of Pennsylvania in August 2019. He also received an M.S. degree in Robotics and M.A. degree in Philosophy at Penn. Before Penn, he obtained an M.Sc. degree in Electrical and Computer Engineering from the University of Waterloo, and his B.Sc. degree in Electrical Engineering and B.Sc. degree in Mathematics from the Sharif University of Technology. His current research area is machine learning in time-dependent and data-scarce regimes.
Host: Dr. Richard M. Leahy
Webcast: https://usc.zoom.us/j/97552157471?pwd=RnVGWm10RlRORFU0cG5RYWVWU0R0Zz09More Information: Seminar Announcement-Rostami-111822.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 539
WebCast Link: https://usc.zoom.us/j/97552157471?pwd=RnVGWm10RlRORFU0cG5RYWVWU0R0Zz09
Audiences: Everyone Is Invited
Contact: Mayumi Thrasher
-
PhD Thesis Proposal - Zimo Li
Fri, Nov 18, 2022 @ 02:00 PM - 03:30 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Candidate: Zimo Li
Title: Human Appearance and Performance Synthesis Using Deep Learning
Committee:
Stefanos Nikolaidis
Aiichiro Nakano
Andrew Nealen
Lauren Itti
Mike Zyda
Abstract:
Synthesis of human performances is a highly sought after technology in several industries. In this presentation, we will go over several new deep learning solutions which tackle the problems of human facial and body performance synthesis.
Facial performance synthesis is a complex multi-step graphics problem. First, the "target" performance to be modified must be tracked and captured accurately. Then, based on the desired modification (whether to change the identity, facial expressions, or both), a modified "source performance" must be synthesized and/or captured from a different actor. Finally, the original facial performance must be removed and replaced with the synthesized one. This multi-step process poses many unique challenges. Using conventional CG tracking and retargeting of expressions from the source to target using a 3D mesh and static texture will give an undesired "rubbery skin" effect. Furthermore, inaccuracies in the expression tracking of the source performance using a blendshape model will result in the "uncanny valley" effect in the output performance. It is often necessary to use costly capture methods, such as a Light Stage, to obtain highly accurate 3D captures and dynamic textures of a source performance in order to avoid these pitfalls. Even then, final modified performances are often uncanny.
When dealing with human body-motion synthesis, creating new motions often requires manual artist animations, tracking new motions on an actor, or stitching together subsequences of previous animations. These methods are limited by cost, or are not able to generate appreciably novel motions.
Over the last several years, the advancement of AI-based generation techniques have let us address many of these issues. In this presentation, we will go over several novel techniques which reduce the cost (time/money/ease-of-access), and/or improve the quality of facial re-enactment, as well as body motion synthesis, pipelines. The applications of these techniques allow us to tackle new problem settings in an efficient way, including visual dubbing (changing the lip motions of a facial performance), dynamic texture synthesis, 3D model generation, as well as extended human motion synthesis.
WebCast Link: https://us05web.zoom.us/j/81890781474?pwd=cjQ3YkVDT3drMlQ2VWtlbjU2YWxyZz09
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
