Plugin estimation of smooth optimal transport maps

T Manole, S Balakrishnan, J Niles-Weed… - The Annals of …, 2024‏ - projecteuclid.org
Plugin estimation of smooth optimal transport maps Page 1 The Annals of Statistics 2024, Vol.
52, No. 3, 966–998 https://doi.org/10.1214/24-AOS2379 © Institute of Mathematical Statistics …

The information bottleneck problem and its applications in machine learning

Z Goldfeld, Y Polyanskiy - IEEE Journal on Selected Areas in …, 2020‏ - ieeexplore.ieee.org
Inference capabilities of machine learning (ML) systems skyrocketed in recent years, now
playing a pivotal role in various aspect of society. The goal in statistical learning is to use …

Information theory with kernel methods

F Bach - IEEE Transactions on Information Theory, 2022‏ - ieeexplore.ieee.org
We consider the analysis of probability distributions through their associated covariance
operators from reproducing kernel Hilbert spaces. We show that the von Neumann entropy …

Sliced mutual information: A scalable measure of statistical dependence

Z Goldfeld, K Greenewald - Advances in Neural Information …, 2021‏ - proceedings.neurips.cc
Mutual information (MI) is a fundamental measure of statistical dependence, with a myriad of
applications to information theory, statistics, and machine learning. While it possesses many …

Geometric lower bounds for distributed parameter estimation under communication constraints

Y Han, A Özgür, T Weissman - Conference On Learning …, 2018‏ - proceedings.mlr.press
We consider parameter estimation in distributed networks, where each sensor in the network
observes an independent sample from an underlying distribution and has $ k $ bits to …

Neural estimation of statistical divergences

S Sreekumar, Z Goldfeld - Journal of machine learning research, 2022‏ - jmlr.org
Statistical divergences (SDs), which quantify the dissimilarity between probability
distributions, are a basic constituent of statistical inference and machine learning. A modern …

The boltzmann policy distribution: Accounting for systematic suboptimality in human models

C Laidlaw, A Dragan - arxiv preprint arxiv:2204.10759, 2022‏ - arxiv.org
Models of human behavior for prediction and collaboration tend to fall into two categories:
ones that learn from large amounts of data via imitation learning, and ones that assume …

Convergence of smoothed empirical measures with applications to entropy estimation

Z Goldfeld, K Greenewald, J Niles-Weed… - IEEE Transactions …, 2020‏ - ieeexplore.ieee.org
This paper studies convergence of empirical measures smoothed by a Gaussian kernel.
Specifically, consider approximating P* N σ, for N σ=△ N (0, σ 2 I d), by P̑ n* N σ under …

[HTML][HTML] Empirical estimation of information measures: A literature guide

S Verdú - Entropy, 2019‏ - mdpi.com
We give a brief survey of the literature on the empirical estimation of entropy, differential
entropy, relative entropy, mutual information and related information measures. While those …

Estimation based on nearest neighbor matching: from density ratio to average treatment effect

Z Lin, P Ding, F Han - Econometrica, 2023‏ - Wiley Online Library
Nearest neighbor (NN) matching is widely used in observational studies for causal effects.
Abadie and Imbens (2006) provided the first large‐sample analysis of NN matching. Their …