Date & Time:
March 26, 2020 10:30 am – 11:30 am
Location:
Live Stream
03/26/2020 10:30 AM 03/26/2020 11:30 AM America/Chicago Vidya Muthukumar (Berkeley) – Fundamental Perspectives on Machine Learning: Strategic Agents and Contemporary Models Live Stream

Fundamental Perspectives on Machine Learning: Strategic Agents and Contemporary Models

Through recent advances in machine learning (ML) technology, we are getting closer to realizing the broadly stated goal of “artificially intelligent”, autonomous agents. In many cases — like cognitive radio, swarm robotics, and e-commerce — these agents will not be acting in isolation, and it is critical for them to directly interact with other agents who themselves behave strategically. The ensuing questions of how agents should learn from strategically generated data, and how such strategic behavior will manifest, are well-posed even when simple ML algorithms are used. On the other hand, most of the recent empirical success in single-agent AI is driven by the construction of overparameterized neural networks that would traditionally be considered too complex for reliable performance. Foundational mechanisms for understanding their state-of-the-art empirical performance remain elusive.

In this talk, I present two vignettes of my research that engage separately with the central difficulties in strategic learning and contemporary models from a fundamental perspective. First, I present a scheme by which an agent can provably learn from an unknown environment, by adapting online to the model that seems to best describe the data while remaining robust to strategically generated data. I also briefly touch upon credible approximations to how strategic agents will behave in the presence of such adaptive learning. Next, I present a signal-processing perspective on the overparameterized (high-dimensional) linear model, and ramifications for generalization in least-squares regression and classification. In addition to the commonly discussed pitfall of noise overfitting, I show that a phenomenon of signal “bleed”, observed classically in statistical signal processing and under-sampling theory, is equally dangerous for generalization. I use these phenomena to characterize special situations in which overparameterization is actually beneficial. I conclude with future directions that I plan to address for a more complete foundational understanding of multi-agent learning.

If you are affiliated with UChicago CS and would like to attend this talk remotely, contact rmitchum@uchicago.edu for links.

Host: Rebecca Willett

Vidya Muthukumar

PhD Student, University of California, Berkeley

Vidya Muthukumar is a final year graduate student in the EECS department at the University of California, Berkeley, advised by Anant Sahai. Her broad interests are in game theory, online and statistical learning. Recently, she is particularly interested in designing learning algorithms that provably adapt in strategic environments, fundamental properties of overparameterized models, and fairness, accountability and transparency in machine learning. Her honors include the IBM Research Science for Social Good Fellowship, SanDisk Fellowship and the UC Berkeley EECS Outstanding Course Development and Teaching Award. She served as co-president of UC Berkeley Women in Computer Science and Engineering (WICSE) in the academic year 2016-2017.

Related News & Events

Video

“Machine Learning Foundations Accelerate Innovation and Promote Trustworthiness” by Rebecca Willett

Jan 26, 2024
Video

Nightshade: Data Poisoning to Fight Generative AI with Ben Zhao

Jan 23, 2024
No Name

High School Students In The Collegiate Scholars Program Get To Know Robots

Nov 14, 2023
No Name

Five UChicago CS students named to Siebel Scholars Class of 2024

Oct 02, 2023
No Name

UChicago Computer Scientists Design Small Backpack That Mimics Big Sensations

Sep 11, 2023
No Name

In The News: U.N. Officials Urge Regulation of Artificial Intelligence

"Security Council members said they feared that a new technology might prove a major threat to world peace."
Jul 27, 2023
No Name

UChicago Computer Scientists Bring in Generative Neural Networks to Stop Real-Time Video From Lagging

Jun 29, 2023
No Name

Computer Science Class Shows Students How To Successfully Create Circuit Boards Without Engineering Experience

May 17, 2023
No Name

UChicago CS Researchers Shine at CHI 2023 with 12 Papers and Multiple Awards

Apr 19, 2023
No Name

New Prototypes AeroRigUI and ThrowIO Take Spatial Interaction to New Heights – Literally

Apr 18, 2023
No Name

Computer Science Displays Catch Attention at MSI’s Annual Robot Block Party

Apr 07, 2023
No Name

UChicago, Stanford Researchers Explore How Robots and Computers Can Help Strangers Have Meaningful In-Person Conversations

Mar 29, 2023
arrow-down-largearrow-left-largearrow-right-large-greyarrow-right-large-yellowarrow-right-largearrow-right-smallbutton-arrowclosedocumentfacebookfacet-arrow-down-whitefacet-arrow-downPage 1CheckedCheckedicon-apple-t5backgroundLayer 1icon-google-t5icon-office365-t5icon-outlook-t5backgroundLayer 1icon-outlookcom-t5backgroundLayer 1icon-yahoo-t5backgroundLayer 1internal-yellowinternalintranetlinkedinlinkoutpauseplaypresentationsearch-bluesearchshareslider-arrow-nextslider-arrow-prevtwittervideoyoutube