Stochastics and Statistics Seminar Series

  1. Events
  2. Stochastics and Statistics Seminar Series

Views Navigation

Event Views Navigation

Today

Sample-optimal inference, computational thresholds, and the methods of moments 

E18-304 , United States

The Stochastics and Statistics Seminar is a weekly meeting organized by the Statistics and Data Science Center (SDSC). It consists of a series of one-hour presentations by worldwide leaders making cutting edge contributions to methodological and theoretical advances in data science. These fields include probability, statistics, optimization, and applied mathematics. The seminar also regularly features…

Active learning with seed examples and search queries

E18-304 , United States

The Stochastics and Statistics Seminar is a weekly meeting organized by the Statistics and Data Science Center (SDSC). It consists of a series of one-hour presentations by worldwide leaders making cutting edge contributions to methodological and theoretical advances in data science. These fields include probability, statistics, optimization, and applied mathematics. The seminar also regularly features…

Testing properties of distributions over big domains

32-141 , United States

The Stochastics and Statistics Seminar is a weekly meeting organized by the Statistics and Data Science Center (SDSC). It consists of a series of one-hour presentations by worldwide leaders making cutting edge contributions to methodological and theoretical advances in data science. These fields include probability, statistics, optimization, and applied mathematics. The seminar also regularly features…

Some related phase transitions in phylogenetics and social network analysis 

E18-304 , United States

The Stochastics and Statistics Seminar is a weekly meeting organized by the Statistics and Data Science Center (SDSC). It consists of a series of one-hour presentations by worldwide leaders making cutting edge contributions to methodological and theoretical advances in data science. These fields include probability, statistics, optimization, and applied mathematics. The seminar also regularly features…

Invariance and Causality

E18-304 , United States

The Stochastics and Statistics Seminar is a weekly meeting organized by the Statistics and Data Science Center (SDSC). It consists of a series of one-hour presentations by worldwide leaders making cutting edge contributions to methodological and theoretical advances in data science. These fields include probability, statistics, optimization, and applied mathematics. The seminar also regularly features…

Fast Rates for Bandit Optimization with Upper-Confidence Frank-Wolfe

E18-304 , United States

The Stochastics and Statistics Seminar is a weekly meeting organized by the Statistics and Data Science Center (SDSC). It consists of a series of one-hour presentations by worldwide leaders making cutting edge contributions to methodological and theoretical advances in data science. These fields include probability, statistics, optimization, and applied mathematics. The seminar also regularly features…

New Provable Techniques for Learning and Inference in Probabilistic Graphical Models

MIT Building E18, Room 304 Ford Building (E18), 50 Ames Street, Cambridge, MA, United States

Speaker: Andrej Risteski (Princeton University) A common theme in machine learning is succinct modeling of distributions over large domains. Probabilistic graphical models are one of the most expressive frameworks for doing this. The two major tasks involving graphical models are learning and inference. Learning is the task of calculating the “best fit” model parameters from…


© MIT Institute for Data, Systems, and Society | 77 Massachusetts Avenue | Cambridge, MA 02139-4307 | 617-253-1764 |