Online Seminar on Mathematical Foundations of Data Science

A weekly online seminar on random topics on mathematical foundations of machine learning, statistics and optimization Sponsored by Two Sigma

Two Sigma Fellowship

Our sponsor, Two Sigma, is soliciting applications for TWO SIGMA PHD FELLOWSHIP and TWO SIGMA DIVERSITY PHD FELLOWSHIP.

Mailing List and Calendar

For announcements and Zoom/Facebook live streaming links, please subscribe to our mailing list.

You may add the talks to your calendar by clicking here.

To ask the speaker a question...

To ask the speaker a question, please use the Q&A function in Zoom to type your questions. The moderator (Zhuoran Yang) will collect questions through the talk and ask the questions after the talk.

Next Speaker: Itai Ashlagi, Stanford University

Date/Time: Friday, 10/29, 11am EDT [Zoom Link]

Title: Price Discovery in Waiting Lists: A Connection to Stochastic Gradient Descent

Abstract: Waiting lists allocate items by offering agents a choice among items with associated waiting times. These waiting times serve as prices that are determined endogenously and adjust according to the stochastic arrivals and departures of agents. We study the allocative efficiency under such dynamically adjusting prices by drawing a connection between this price adjustment process and the stochastic gradient descent optimization algorithm. We show that the loss due to price fluctuations is bounded by the granularity of price changes. Additional conditions allow us to identify markets where the loss is close to the bound or exponentially small. Our results show that a simple price adjustment heuristic can perform well, but may be slow to adjust to changes in demand because of a trade-off between the speed of adaptation and loss from price fluctuations.

Joint work with Jacob Leshno, Amin Saberi and Pengyu Qian

Bio: Itai Ashlagi is an Associate Professor at the Management Science & Engineering Department. He is interested in game theory and the design and analysis of marketplaces. He is especially interested in marketplaces, in which matching is an essential activity. markets, for which he developed mechanisms using tools from operations/cs and economics. His work influenced the practice of Kidney exchange, for which he has become a Franz Edelman Laureate. Ashlagi received his PhD in operations research from the Technion-Israel Institute of Technology. Before coming to Stanford he was an assistant professor of Operations Management at Sloan, MIT and prior to that a postdoctoral researcher at HBS. He is the recipient of the outstanding paper award in the ACM conference of Electronic Commerce 2009. His research is supported by the NSF including an NSF-CAREER award.

Upcoming Speakers

Itai Ashlagi

Stanford University

Title: TBA

Date/Time: Friday October 29th 11am EDT

Alekh Agarwal

Microsoft Research

Title: TBA

Date/Time: Friday November 5th 11am

Jiawei Han

UIUC

Title: TBA

Date/Time: Friday November 12th 11am

Vasilis Syrgkanis

Microsoft Research

Title: TBA

Date/Time: Friday November 19th 11am

Lars Peter Hansen

University of Chicago

Title: TBA

Date/Time: Friday December 3rd 11am

Jose Blanchet

Stanford University

Title: TBA

Date/Time: Friday December 10th 12pm

Tianxi Cai

Harvard University

Title: TBA

Date/Time: TBA

Organizers

If you have any questions, please feel free to contact the organizers.

Ethan X. Fang, Niao He, Junwei Lu, Zhaoran Wang, Zhuoran Yang, Tuo Zhao

Ethan X. Fang

Penn State University

Niao He

ETH Zurich

Junwei Lu

Harvard University

Zhaoran Wang

Northwestern University

Zhuoran Yang

Princeton University

Tuo Zhao

Georgia Institute of Technology

Previous Talks (Including Recordings)

Adrian S. Lewis

Cornell University

Title: Smoothness in Nonsmooth Optimization

Date/Time: July 7th 3pm EDT

Recording

Samory Kpotufe

Columbia University

Title: Some Recent Insights on Transfer-Learning

Date/Time: July 21th 3pm EDT

Recording

Eric J. Tchetgen Tchetgen

The Wharton School, UPenn

Title: TBA

Date/Time: July 28th 3pm EDT

Recording

John Urschel

MIT

Title: TBA

Date/Time: August 4th 3pm EDT

Recording

Michael I. Jordan

UC Berkeley

Title: Optimization with Momentum: Dynamical, Variational, and Symplectic Perspectives

Date/Time: August 11th 3pm EDT

Recording

Devavrat Shah

MIT

Title: Synthetic Interventions

Date/Time: August 18th 3pm EDT

Recording

James Robins

Harvard University

Title: On Nearly Assumption-Free Tests of Nominal Confidence Interval Coverage for Causal Parameters Estimated by Machine Learning

Date/Time: September 1st 3pm EDT

Recording

Lin Xiao

Microsoft Research

Title: Statistical Optimization Methods for Machine Learning

Date/Time: Tuesday Sep 15th 3pm EDT

Recording

Jim Dai

Cornell University

Title: Queueing Network Controls via Deep Reinforcement Learning

Date/Time: Friday Sep 25th 11am EDT

Recording

Amir Ali Ahmadi

Princeton University

Title: Learning Dynamical Systems with Side Information

Date/Time: Friday Oct 2nd 11am EDT

Recording

Susan Murphy

Harvard University

Title: Off-Policy Estimation of Long-Term Average Outcomes with Applications to Mobile Health

Date/Time: Friday Oct 9th 11am EDT

Recording

Ming Yuan

Columbia University

Title: Complexity of High Dimensional Sparse Functions

Date/Time: Friday Nov 13th 11am EST

Recording

Hongyu Zhao

Yale University

Title: Predicting Disease Risk from Genomics Data

Date/Time: Tuesday Nov 17th 11am EST

Recording

Peter Bartlett

UC Berkeley

Title: Benign Overfitting

Date/Time: Friday Dec 4th 3pm EDT

Recording

Yuejie Chi

Carnegie Mellon University

Title: Preconditioning Helps: Faster Convergence in Statistical and Reinforcement Learning

Date/Time: Friday Jan 15th 11am EDT

Recording

Xi Chen

New York University

Title: Robust Online Learning and its Applications to Assortment Optimization

Date/Time: Friday Jan 22th 4pm EDT

Recording

Adam Wierman

California Institute of Technology

Title: Competitive Control via Online Optimization

Date/Time: Friday Jan 29th 11am EDT

Recording

Dimitris Bertsimas

Massachusetts Institute of Technology

Title: Machine Learning under a Modern Optimization Lens

Date/Time: Friday Feb 5th 11am EST

Recording

Csaba Szepesvari

University of Alberta/DeepMind

Title: Hardness of MDP Planning with Linear Function Approximation

Date/Time: Friday Feb 12th 11am EST

Recording

Yan Liu

University of Southern California

Title: Deciphering Neural Networks through the Lens of Feature Interactions

Date/Time: Friday Feb 26th 3pm EST

Recording

Na Li

Harvard University

Title: Real-Time Distributed Decision Making in Networked Systems

Date/Time: Friday Mar 26th 11am EDT

Recording

Sebastien Bubeck

Microsoft Research

Title: A law of robustness for two-layers neural networks

Date/Time: Friday April 2nd 11am EDT

Recording

Harrison Zhou

Yale University

Title: Global Convergence of EM?

Date/Time: Friday Apr 9th 11am EDT

Recording

Vivek Farias

Massachusetts Institute of Technology

Title: Causal Inference for Panel Data with General Treatment Patterns

Date/Time: Friday Apr 16th 11am EDT

Recording

Constantine Caramanis

University of Texas, Austin

Title: MLE and EM Algorithms for Log-Concave Mixtures

Date/Time: Friday Apr 23th 11am EDT

Recording

Jorge Nocedal

Northwestern University

Title: Derivative-Free Optimization of Noisy Functions

Date/Time: Friday April 30th 11am EDT

Recording

Daniel Spielman

Yale University

Title: Balancing Covaraites in Randomized Experiments

Date/Time: Friday May 7th 11am EDT

Recording

Rebecca Willet

University of Chicago

Title: Machine Learning and Inverse Problems in Imaging

Date/Time: Friday May 14th 11am EDT

Recording

Matias Cattaneo

Princeton University

Title: On Binscatter

Date/Time: Friday May 21st 11am EDT

Recording

Stephen Wright

University of Wisconsin-Madison

Title: The role of Complexity Bounds in Optimization

Date/Time: Friday June 4th 11am EDT

Recording

Melvyn Sim

National University of Singapore

Title: The Dao of Robustness

Date/Time: Friday July 9th 11am EDT

Recording

Yao Xie

Georgia Institute of Technology

Title: Statistical Inference for Spatio-Temporal Point Process

Date/Time: Friday July 16th 11am EDT

Recording

John Birge

University of Chicago

Title: Optimization and Estimation in High Dimensions

Date/Time: Friday July 23rd 11am EDT

Recording

Peng Sun

Duke University

Title: Continuous Time Contract Design and Stochastic Optimal Control

Date/Time: Friday August 6th 11am EDT

Recording

Jason Hartline

Northwestern University

Title: TBA

Date/Time: Friday August 20th 11am EDT

Recording

Haoda Fu

Eli Lilly

Title: Our Recent Development on Cost Constraint Machine Learning Models

Date/Time: Friday September 24th 12pm EDT

Recording

Yihong Wu

Yale University

Title: Recent Results in Planted Assignment Problems

Date/Time: Friday October 1st 11am EDT

Huseyin Topaloglu

Cornell Tech

Title: Joint Assortment Optimization

Date/Time: Friday October 15th 11am EDT

Jas Sekhon

Yale University

Title: Estimating Heterogeneous Treatment Effects Using Machine Learning

Date/Time: Friday October 22nd 11am EDT

Sponsors