Select a calendar:
Filter March Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for March 10, 2021
-
CS Colloquium: Hongyang Zhang (Toyota Technological Institute) - New Advances in (Adversarially) Robust and Secure Machine Learning
Wed, Mar 10, 2021 @ 09:00 AM - 10:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Hongyang Zhang , Toyota Technological Institute
Talk Title: New Advances in (Adversarially) Robust and Secure Machine Learning
Series: CS Colloquium
Abstract: Deep learning models are often vulnerable to adversarial examples. In this talk, we will focus on robustness and security of machine learning against adversarial examples. There are two types of defenses against such attacks: 1) empirical and 2) certified adversarial robustness.
In the first part of the talk, we will see the foundation of our winning system, TRADES, in the NeurIPS'18 Adversarial Vision Challenge in which we won 1st place out of 400 teams and 3,000 submissions. Our study is motivated by an intrinsic trade-off between robustness and accuracy: we provide a differentiable and tight surrogate loss for the trade-off using the theory of classification-calibrated loss. TRADES has record-breaking performance in various standard benchmarks and challenges, including the adversarial benchmark RobustBench, the NLP benchmark GLUE, the Unrestricted Adversarial Examples Challenge hosted by Google, and has motivated many new attacking methods powered by our TRADES benchmark.
In the second part of the talk, to equip empirical robustness with certification, we study certified adversarial robustness by random smoothing. On one hand, we show that random smoothing on the TRADES-trained classifier achieves SOTA certified robustness when the perturbation radius is small. On the other hand, when the perturbation is large, i.e., independent of inverse of input dimension, we show that random smoothing is provably unable to certify L_infty robustness for arbitrary random noise distribution. The intuition behind our theory reveals an intrinsic difficulty of achieving certified robustness by "random noise based methods", and inspires new directions as potential future work.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Hongyang Zhang is a Postdoc fellow at Toyota Technological Institute at Chicago, hosted by Avrim Blum and Greg Shakhnarovich. He obtained his Ph.D. from CMU Machine Learning Department in 2019, advised by Maria-Florina Balcan and David P. Woodruff. His research interests lie in the intersection between theory and practice of machine learning, robustness and AI security. His methods won the championship or ranked top in various competitions such as the NeurIPS'18 Adversarial Vision Challenge (all three tracks), the Unrestricted Adversarial Examples Challenge hosted by Google, and the NeurIPS'20 Challenge on Predicting Generalization of Deep Learning. He also authored a book in 2017.
Host: David Kempe
Audiences: By invitation only.
Contact: Assistant to CS chair
-
CANCELLED - Computer Science General Faculty Meeting
Wed, Mar 10, 2021 @ 12:00 PM - 02:00 PM
Thomas Lord Department of Computer Science
Receptions & Special Events
Bi-Weekly regular faculty meeting for invited full-time Computer Science faculty only. Event details emailed directly to attendees.
Location: TBD
Audiences: Invited Faculty Only
Contact: Assistant to CS chair
-
DEN@Viterbi: How to Apply Virtual Info Session
Wed, Mar 10, 2021 @ 12:00 PM - 01:00 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=e25087b2d448ff393d7feb8469c8e8e30
Audiences: Everyone Is Invited
Contact: Corporate & Professional Programs
-
Undergraduate Advisement Drop-in HoursWed, Mar 10, 2021 @ 01:30 PM - 02:30 PM
Thomas Lord Department of Computer Science
Workshops & Infosessions
Do you have a quick question? The CS advisement team will be available for drop-in live chat advisement for declared undergraduate students in our four majors during the spring semester on Tuesdays, Wednesdays, and Thursdays from 1:30pm to 2:30pm Pacific Time. Access the live chat on our website at: https://www.cs.usc.edu/chat/
Location: Online
Audiences: Undergrad
Contact: USC Computer Science
-
Center for Cyber-Physical Systems and Internet of Things and Ming Hsieh Institute Seminar
Wed, Mar 10, 2021 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Somil Bansal, Department of Electrical Engineering and Computer Sciences, University of California, Berkeley
Talk Title: Safe and Data-efficient Learning for Robotics
Series: Center for Cyber-Physical Systems and Internet of Things
Abstract: For successful integration of autonomous systems such as drones and self-driving cars in our day-to-day life, they must be able to quickly adapt to ever-changing environments, and actively reason about their safety and that of other users and autonomous systems around them. Even though control-theoretic approaches have been used for decades now for the control and safety analysis of autonomous systems, these approaches typically operate under the assumption of a known system dynamics model and the environment in which the system is operating. To overcome these challenges, machine learning approaches have been explored to operate autonomous systems intelligently and reliably in unpredictable environments based on prior data. However, learning techniques widely used today are extremely data inefficient, making it challenging to apply them to real-world physical systems. Moreover, they lack the necessary mathematical framework to provide guarantees on correctness, causing safety concerns as data-driven physical systems are integrated in our society.
In this talk, we will present a toolbox of methods combining robust optimal control with data-driven techniques inspired by machine learning, to enable performance improvement while maintaining safety. In particular, we design modular architectures that combine system dynamics models with modern learning-based perception approaches to solve challenging perception and control problems in a priori unknown environments in a data-efficient fashion. These approaches are demonstrated on a variety of ground robots navigating in unknown buildings around humans based only on onboard visual sensors. Next, we discuss how we can use optimal control methods not only for data-efficient learning, but also to monitor and recognize the learning system's failures, and to provide online corrective safe actions when necessary. This allows us to provide safety assurances for learning-enabled systems in unknown and human-centric environments, which has remained a challenge to date.
Biography: Somil Bansal completed his MS and PhD in the Electrical Engineering and Computer Sciences Department at the University of California, Berkeley in 2014 and 2020 respectively, and received his B.Tech. in Electrical Engineering from Indian Institute of Technology, Kanpur in 2012. He is currently spending a year as a research scientist at Waymo. In Fall 2021, he will join as an Assistant Professor in the Department of Electrical and Computer Engineering at the University of Southern California, Los Angeles. His research interests include developing mathematical tools and algorithms for control and analysis of autonomous systems, with a focus on bridging learning and control-theoretic approaches for safety-critical autonomous systems. Somil has received several awards, most notably the Eli Jury award and the outstanding graduate student instructor award at UC Berkeley, and the academic excellence award at IIT Kanpur.
Host: Pierluigi Nuzzo, nuzzo@usc.edu
Webcast: https://usc.zoom.us/webinar/register/WN_Qk4-7AthThudso7LXs2OiALocation: Online
WebCast Link: https://usc.zoom.us/webinar/register/WN_Qk4-7AthThudso7LXs2OiA
Audiences: Everyone Is Invited
Contact: Talyia White
-
AME Seminar
Wed, Mar 10, 2021 @ 03:30 PM - 04:30 PM
Aerospace and Mechanical Engineering
Conferences, Lectures, & Seminars
Speaker: George Park, University of Pennsylvania
Talk Title: Toward Predictive Yet Affordable Computations of Practical Wall-Bounded Turbulent Flows
Abstract: Kinetic energy of turbulence is generated at large scales controlled by boundary conditions, but it is dissipated into heat at the smallest scales. The ratio of these two length scales increases rapidly with Reynolds number. Solid walls add another dimension in this scale landscape, where the scale separation gets progressively less pronounced toward the wall. This has significant ramifications on the cost of scale-resolving simulation of practical engineering flows, such as those found in aircraft, wind turbines, and ship hydrodynamics. Direct approaches with full resolution of length and times scales close to the wall are still infeasible with current computing power. The demand for superior designs at reduced cost has led researchers to explore alternative computational approaches that have potential to be predictive yet affordable. Large-eddy simulation (LES) is one such approach where only the energy-containing scales are resolved directly, and the effect of the unresolved motions are modeled. In practical LES calculations, subgrid-scale (SGS) models are used in conjunction with wall models to augment the turbulent shear stress, which otherwise is underpredicted on coarse grids and leads to inaccurate prediction of mean and turbulence quantities.
In this talk, I will discuss the research in my group on this wall-modeled LES approach. Widely used wall-modeling techniques will be discussed with their applications to canonical and complex wall-bounded flows. Challenges in robust and efficient implementation of the models in flow solvers for handling practical geometries will be discussed. I will also highlight recent work to predict flow over realistic aircraft geometries at flight conditions and a boundary layer with mean three dimensionality.
Biography: George Park is an Assistant Professor of Mechanical Engineering and Applied Mechanics at the University of Pennsylvania. He received his Ph.D. and M.S. in Mechanical Engineering (ME) from Stanford University in 2014 and 2011, respectively, and his B.S. in ME from Seoul National University, South Korea in 2009. He worked as a postdoctoral fellow and an engineering research associate at the Center for Turbulence Research (Stanford) prior to joining UPenn as a faculty member in 2018. His research interests include high-fidelity numerical simulation of complex wall-bounded turbulent flows, computational methods with unstructured grids, non-equilibrium turbulent boundary layers, and fluid-structure interaction.
Host: AME Department
More Info: https://usc.zoom.us/j/97491401429
Webcast: https://usc.zoom.us/j/97491401429Location: Online event
WebCast Link: https://usc.zoom.us/j/97491401429
Audiences: Everyone Is Invited
Contact: Tessa Yao
Event Link: https://usc.zoom.us/j/97491401429
-
Key Virtual Job Search Tips with Northrop Grumman
Wed, Mar 10, 2021 @ 04:00 PM - 04:30 PM
Viterbi School of Engineering Career Connections
University Calendar
Hear from Northrop Grumman recruiter (and USC alumni) Anjali Chopra about how to navigate your job search in a virtual world. This workshop will include tips for virtual networking events/job fairs, security tips, virtual interviewing preparation, how to succeed in an online interview.
RSVP through Viterbi Career Gateway > Events > Workshops
Audiences: Everyone Is Invited
Contact: RTH 218 Viterbi Career Connections
-
CS Colloquium: Vered Shwartz (University of Washington) - Commonsense Knowledge and Reasoning in Natural Language
Wed, Mar 10, 2021 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Vered Shwartz, University of Washington
Talk Title: Commonsense Knowledge and Reasoning in Natural Language
Series: CS Colloquium
Abstract: Natural language understanding models are trained on a sample of the situations they may encounter. Commonsense and world knowledge, and language understanding and reasoning abilities can help them address unknown situations sensibly. This talk will discuss several lines of work addressing commonsense knowledge and reasoning in natural language. First, I will introduce a new paradigm for commonsense reasoning tasks with introspective knowledge discovery through a process of self-asking information seeking questions ("what is the definition of...") and answering them. Second, I will present work on nonmonotonic reasoning in natural language, a core human reasoning ability that has been studied in classical AI but mostly overlooked in modern NLP, including abductive reasoning (reasoning about plausible explanations), counterfactual reasoning (what if?) and defeasible reasoning (updating beliefs given additional information). Next, I will discuss how generalizing existing knowledge can help language understanding, and demonstrate it for noun compound paraphrasing (e.g. olive oil is "oil made of olives"). I will conclude with open problems and future directions in language, knowledge, and reasoning.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Vered Shwartz is a postdoctoral researcher at the Allen Institute for AI (AI2) and the Paul G. Allen School of Computer Science & Engineering at the University of Washington, working with Yejin Choi. Vered's research interests are in NLP, AI, and machine learning, particularly focusing on commonsense knowledge and reasoning, computational semantics, discourse and pragmatics. Previously, Vered completed her PhD in Computer Science from Bar-Ilan University, under the supervision of Ido Dagan. Vered's work has been recognized with several awards, including The Eric and Wendy Schmidt Postdoctoral Award for Women in Mathematical and Computing Sciences, the Clore Foundation Scholarship, and an ACL 2016 outstanding paper award.
Host: Xiang Ren
Audiences: By invitation only.
Contact: Assistant to CS chair
