News & Events

GMOS

Geometric Methods in Optimization and Sampling Boot Camp

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.

Read More
CCSI

Computational Complexity of Statistical Inference Boot Camp

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.

Read More

FODSI Seminar

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

FODSI Seminar

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

FODSI Seminar

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

FODSI Seminar

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

FODSI Seminar

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

FODSI Seminar

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

FODSI Seminar

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

FODSI Seminar

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

Watch video

FODSI Seminar

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

FODSI Seminar

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

FODSI Kickoff Meeting

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

Watch videos

FODSI Seminar

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

Watch video

FODSI Seminar

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

Watch video

FODSI Seminar

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

Watch video

FODSI Seminar

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

Watch video
NSF announcement

NSF Announces $12.5M Award

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.

Read More