An Improved Uniform Convergence Bound with Fat-Shattering Dimension

07/13/2023
by   Roberto Colomboni, et al.
0

The fat-shattering dimension characterizes the uniform convergence property of real-valued functions. The state-of-the-art upper bounds feature a multiplicative squared logarithmic factor on the sample complexity, leaving an open gap with the existing lower bound. We provide an improved uniform convergence bound that closes this gap.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/21/2023

Prediction, Learning, Uniform Convergence, and Scale-sensitive Dimensions

We present a new general-purpose algorithm for learning classes of [0,1]...
research
03/08/2021

Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models

Recent work showed that there could be a large gap between the classical...
research
09/11/2018

A Fixed-Depth Size-Hierarchy Theorem for AC^0[⊕] via the Coin Problem

We prove the first Fixed-depth Size-hierarchy Theorem for uniform AC^0[⊕...
research
06/10/2018

On closeness to k-wise uniformity

A probability distribution over -1, 1^n is (eps, k)-wise uniform if, rou...
research
04/18/2023

Optimal PAC Bounds Without Uniform Convergence

In statistical learning theory, determining the sample complexity of rea...
research
11/19/2021

Uniform Brackets, Containers, and Combinatorial Macbeath Regions

We study the connections between three seemingly different combinatorial...
research
07/07/2020

Near Optimal Provable Uniform Convergence in Off-Policy Evaluation for Reinforcement Learning

The Off-Policy Evaluation aims at estimating the performance of target p...

Please sign up or login with your details

Forgot password? Click here to reset