On the Statistical Complexity of Sample Amplification

01/12/2022
by   Brian Axelrod, et al.
0

Given n i.i.d. samples drawn from an unknown distribution P, when is it possible to produce a larger set of n+m samples which cannot be distinguished from n+m i.i.d. samples drawn from P? (Axelrod et al. 2019) formalized this question as the sample amplification problem, and gave optimal amplification procedures for discrete distributions and Gaussian location models. However, these procedures and associated lower bounds are tailored to the specific distribution classes, and a general statistical understanding of sample amplification is still largely missing. In this work, we place the sample amplification problem on a firm statistical foundation by deriving generally applicable amplification procedures, lower bound techniques and connections to existing statistical notions. Our techniques apply to a large class of distributions including the exponential family, and establish a rigorous connection between sample amplification and distribution learning.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/22/2023

The Sample Complexity of Multi-Distribution Learning for VC Classes

Multi-distribution learning is a natural generalization of PAC learning ...
research
08/09/2020

Testing Determinantal Point Processes

Determinantal point processes (DPPs) are popular probabilistic models of...
research
05/18/2023

Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models

We focus on the task of learning a single index model σ(w^⋆· x) with res...
research
05/29/2021

Towards a Rigorous Statistical Analysis of Empirical Password Datasets

In this paper we consider the following problem: given N independent sam...
research
07/03/2022

How to Sample Approval Elections?

We study the multifaceted question of how to sample approval elections i...
research
02/14/2019

Dualizing Le Cam's method, with applications to estimating the unseens

One of the most commonly used techniques for proving statistical lower b...
research
10/29/2019

Stein's Lemma for the Reparameterization Trick with Exponential Family Mixtures

Stein's method (Stein, 1973; 1981) is a powerful tool for statistical ap...

Please sign up or login with your details

Forgot password? Click here to reset