Past talk · AI/ML Seminar Series
Statistical implications of group invariance of distributions
Professor of Machine Learning, Gatsby Computational Neuroscience Unit, University College London
- Date & time
- Monday, November 21, 2022 · 1:00 PM
- Location
- Donald Bren Hall 4011
Abstract
Consider a large random structure — a random graph, a stochastic process on the line, a random field on the grid — and a function that depends only on a small part of the structure. Use a family of transformations to move the domain of the function over the structure, collect each function value, and average. Under suitable conditions, the law of large numbers generalizes to such averages. My recent work with Morgane Austern shows that central limit theorems and other higher-order properties also hold: if the i.i.d. assumption of classical statistics is substituted by suitable properties formulated in terms of groups, the fundamental theorems of inference still hold.
About the speaker
Peter Orbanz is a Professor of Machine Learning in the Gatsby Computational Neuroscience Unit at University College London. He studies large systems of dependent variables in machine learning and inference problems, including symmetry and group invariance properties, random graphs, and the intersection of ergodic theory and statistical physics with statistics. He was previously an Associate Professor in the Department of Statistics at Columbia University.