Select a calendar:
Filter September Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for September 16, 2024
-
EiS Communications Hub - Tutoring for Engineering Ph.D. StudentsMon, Sep 16, 2024 @ 10:00 AM - 12:00 PM
Viterbi School of Engineering Student Affairs
Workshops & Infosessions
Come to the EiS Communications Hub for one-on-one tutoring from Viterbi faculty for Ph.D. writing and speaking projects!
Location: Ronald Tutor Hall of Engineering (RTH) - 222A
Audiences: Viterbi Ph.D. Students
Contact: Helen Choi
Event Link: https://sites.google.com/usc.edu/eishub/home
-
Geometric Regularizations for 3D Shape Generation
Mon, Sep 16, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Qixing Huang , Associate Professor, Computer Science Department - University of Texas at Austin
Talk Title: Geometric Regularizations for 3D Shape Generation
Abstract: Generative models, which map a latent parameter space to instances in an ambient space, enjoy various applications in 3D Vision and related domains. A standard scheme of these models is probabilistic, which aligns the induced ambient distribution of a generative model from a prior distribution of the latent space with the empirical ambient distribution of training instances. While this paradigm has proven to be quite successful on images, its current applications in 3D generation encounter fundamental challenges in the limited training data and generalization behavior. The key difference between image generation and shape generation is that 3D shapes possess various priors in geometry, topology, and physical properties. Existing probabilistic 3D generative approaches do not preserve these desired properties, resulting in synthesized shapes with various types of distortions. In this talk, I will discuss recent work that seeks to establish a novel geometric framework for learning shape generators. The key idea is to model various geometric, physical, and topological priors of 3D shapes as suitable regularization losses by developing computational tools in differential geometry and computational topology. We will discuss the applications in deformable shape generation, latent space design, joint shape matching, and 3D man-made shape generation. This research is supported by NSF IIS 2413161.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
https://usc.zoom.us/j/93012253116?pwd=4bJJFbbbfblFHRjabBBvvCuavDml6J.1
Meeting ID: 930 1225 3116
Passcode: 570060
Biography: Qixing Huang is an associate professor with tenure at the computer science department of the University of Texas at Austin. His research sits at the intersection of graphics, geometry, optimization, vision, and machine learning. He has published more than 100 papers at leading venues across these areas. His research has received several awards, including multiple best paper awards, the best dataset award at Symposium on Geometry Processing 2018, IJCAI 2019 early career spotlight, multiple industrial and NSF awards, and 2021 NSF Career award. He has also served as area chairs of CVPR, ECCV, ICCV and technical papers committees of SIGGRAPH and SIGGRAPH Asia, and co-chaired Symposium on Geometry Processing 2020.
Host: Assistant Prof. Yue Wang
Webcast: https://usc.zoom.us/j/93012253116?pwd=4bJJFbbbfblFHRjabBBvvCuavDml6J.1Location: Olin Hall of Engineering (OHE) - 136
WebCast Link: https://usc.zoom.us/j/93012253116?pwd=4bJJFbbbfblFHRjabBBvvCuavDml6J.1
Audiences: Everyone Is Invited
Contact: Thomas Lord Department of Computer Science
-
AI4Health – Computational Epidemiology During the COVID-19 Pandemic
Mon, Sep 16, 2024 @ 11:00 AM - 12:00 PM
Information Sciences Institute
University Calendar
Abstract: In this talk, Professor Majumder will discuss her recent work in computational epidemiology (comp epi): an interdisciplinary field at the intersection of machine learning, digital data, and public health. With a focus on the COVID-19 pandemic, topics covered will include agent-based models for health policy simulation; smartphone mobility data for health policy evaluation; and search query & news media data for monitoring health misinformation. In particular, the health policies and digital data considered will showcase the role of social justice and social networks in Prof. Majumder’s research. Host: Abigail Horn, Research Assistant Professor of Industrial and Systems Engineering. You may sign up here: https://docs.google.com/spreadsheets/d/1Ygbf_dw_Lz2PHkAhkBZKRG7zauEyMjo5/edit?usp=sharing&ouid=115809796864143943107&rtpof=true&sd=true
to speak with Professor Majumder via Zoom between 9 am and 10:30 am, and 12 pm and 2 pm. All times Pacific Speaker Bio Dr. Maimuna (Maia) Majumder (she/they) is an Assistant Professor and Inaugural Peter Szolovits Distinguished Scholar in the Computational Health Informatics Program at Harvard Medical School and Boston Children’s Hospital. Her research applies artificial intelligence & machine learning methods to public health problems, with a focus on infectious disease surveillance using search query, mobile phone, and news & social media data. Since January 2020, Maia and her team have been actively responding to the ongoing COVID-19 pandemic.Location: ONLINE ONLY
Audiences: Everyone Is Invited
Contact: Tricia Olmedo
Event Link: https://usc.zoom.us/j/93936022035?pwd=Ot1rjLPcXteolnG18eVVPJhnrdiBtr.1&from=addon
-
CSC/CommNetS-MHI Seminar: Thomas Zhang
Mon, Sep 16, 2024 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Thomas Zhang, University of Pennsylvania
Talk Title: Guarantees for Representation Learning: Distribution Shift, Optimization, Fewer Samples
Abstract: In many areas of machine learning, it is the general understanding that broadly useful features can be extracted from data across different tasks or domains. This forms the key intuition behind the "pre-train then fine-tune" paradigm, and more generally representation learning (learning the feature mappings) and transfer learning (downstream performance on unseen tasks). Naturally, there has been significant effort to document the benefit of using diverse multi-task data both empirically and theoretically. However, prior works impose various assumptions that greatly affect their applicability, especially in settings involving data generated by dynamical systems, e.g. robotics and control.
In this talk, I will introduce the multi-task representation learning problem, and walk through the pathologies arising from sequential settings, previewed in the talk title. I will then present our recent results addressing many of these issues. In particular, we provide generalization guarantees which illustrate the benefit of learning a shared representation across domains, remaining valid even when there are too few samples to solve each task individually. We then show that optimizing for the representation is surprisingly hard, requiring critical algorithmic modifications to ensure convergence. Lastly, I will show how these results, descended from iid learning, can be lifted to dynamical systems to ensure closed-loop performance.
Biography: Thomas Zhang is a 5th-year PhD student at the University of Pennsylvania advised by Prof. Nikolai Matni. His research interests involve a combination of dynamical systems, statistical learning, and control theory. Prior to Penn, Thomas received BSc’s in Mathematics and Statistics & Data Science from Yale University, where he then spent a year as a research scientist in the Applied Mathematics Program.
Host: Dr. Stephen Tu, stephen.tu@usc.edu
More Information: 2024.09.16 CSC Seminar - Thomas Zhang.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - EEB 132
Audiences: Everyone Is Invited
Contact: Miki Arlen
-
Viterbi- The Trade Desk Recruiting Session
Mon, Sep 16, 2024 @ 06:00 PM - 07:30 PM
Viterbi School of Engineering Career Connections
Workshops & Infosessions
This is for Viterbi engineering students only.
Are you passionate about technology and interested in a dynamic career at the forefront of digital advertising? The Trade Desk invites you to a career exploration panel featuring recent graduates and early career professionals who have successfully launched their careers in programmatic advertising. Our industry experts will share their experiences, career paths, and the exciting opportunities available at The Trade Desk. Whether you're a junior, senior, or master's student, this event is designed to help you explore potential career paths and learn how your engineering skills can make a significant impact in the digital advertising industry. Don't miss this chance to network with The Trade Desk team and discover how you can shape the future of advertising.
Please register on Handshake. If the RSVP is full, please join the waitlist. Waitlist does not guarantee entry, but you are welcome to stop by the event and if there is room, you can attend.Location: Ronald Tutor Hall of Engineering (RTH) - 211
Audiences: BS, MS
Contact: RTH 218 Viterbi Career Connections
Event Link: https://usc.joinhandshake.com/
