News & Events

The boot camp is intended to acquaint participants with the key themes of the program and, by means of tutorials, rapidly bring them to similar levels of knowledge regarding both mathematical tools and applications. The tutorials will be split into two types. On the one hand, fundamental tutorials aim at covering the main tools, techniques, and problems in the field. On the other hand, advanced tutorials aim to present more specialized topics that have recently emerged in the field. Fundamental tutorials will be held in the morning in two lectures of 1.5 hours each. Advanced tutorials will last 1.5 hours each and be held in the afternoon.

The boot camp is intended to acquaint program participants with the key themes of the program. It will consist of five days of tutorial presentations.

Caroline Uhler (MIT). Autoencoders and Causality in the Light of Drug Repurposing for COVID-19.

Cong Ma (UC Berkeley). Minimax Off-Policy Evaluation for Multi-Armed Bandits.

Suvrit Sra (MIT). SGD without replacement: optimal rate analysis and more.

Jiantao Jiao (UC Berkeley). Sharp Minimax Rates for Imitation Learning

Costis Daskalakis (MIT). Equilibrium Computation and the Foundations of Deep Learning

Peng Ding (UC Berkeley). Multiply robust estimation of causal effects under principal ignorability

Michael Jordan (UC Berkeley). Towards a Blend of Machine Learning and Economics

Rong Ge (Duke). A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neural Net.

Arnaud Doucet (Oxford). Perfect Simulation for Feynman-Kac Models using Ensemble Rejection Sampling.

Mary Wooters (Stanford). Sharp Thresholds for Random Subspaces, and Applications.

The FODSI Kickoff meeting took place on on Nov 10, 2020 (virtually). Watch the videos on the Simons Institute Youtube Channel

Carola-Bibiane Schönlieb (Cambridge). Data driven variational models for solving inverse problems.

Alex Andoni (Columbia). Approximating Edit Distance in Near-Linear Time.

Gábor Lugosi (Pompeu Fabra University). On Estimating the Mean of a Random Vector.

Francis Bach (INRIA). Distributed Machine Learning over Networks.

The National Science Foundation has awarded $12.5 million to establish a multidisciplinary institute---a collaboration between UC Berkeley and MIT, partnering with Boston, Northeastern, Harvard and Howard Universities, and Bryn Mawr College---to improve our understanding of critical issues in data science, including modeling, statistical inference, computational efficiency, and societal impacts.