This course teaches learners about lower bounds for statistical inference in distributed and constrained settings. The course covers distributed learning and testing, various models and protocols, as well as different types of distributions. The teaching method involves presenting theoretical concepts and models. This course is intended for individuals interested in statistical inference, distributed systems, and constrained settings.
Cookbook Lower Bounds for Statistical Inference in Distributed and Constrained Settings - Part 1
Overview
Syllabus
Introduction
Distributed Learning and Testing
Example
Model
Protocols
Models
General formulation
Two sets of distributions
Discrete distributions
Distribution over a highdimensional domain
Discrete distribution
References
Outline
Taught by
IEEE FOCS: Foundations of Computer Science
Tags
Related Courses
-
Cookbook - Lower Bounds for Statistical Inference in Distributed and Constrained Settings - Part 4
-
Lower Bounds for Maximal Matchings and Maximal Independent Sets
-
Collaborative Learning with Limited Interaction - Tight Bounds for Distributed Exploration in Bandits
-
Network Coding Gaps for Completion Times of Multiple Unicasts
