paper-with-me

Papers

Profile Entropy: A Fundamental Measure for the Learnability and Compressibility of Distributions

2020-12-01 · NeurIPS 2020 12 · Yi Hao, Alon Orlitsky

The profile of a sample is the multiset of its symbol frequencies. We show that for samples of discrete distributions, profile entropy is a fundamental measure unifying the concepts of estimation, inference, and compression. Specifically, profile entropy: a) determines the speed of estimating the distribution relative to the best natural estimator; b) characterizes the rate of inferring all symmetric properties compared with the best estimator over any label-invariant distribution collection; c) serves as the limit of profile compression, for which we derive optimal near-linear-time block and sequential algorithms. To further our understanding of profile entropy, we investigate its attributes, provide algorithms for approximating its value, and determine its magnitude for numerous structural distribution families.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Profile Entropy: A Fundamental Measure for the Learnability and Compressibility of Discrete Distributions

2020-02-26 · Yi Hao, Alon Orlitsky

The profile of a sample is the multiset of its symbol frequencies. We show that for samples of discrete distributions, profile entropy is a fundamental measure unifying the concepts of estimation, inference, and compress…

On statistical learning via the lens of compression

2016-10-12 · Ofir David, Shay Moran, Amir Yehudayoff

This work continues the study of the relationship between sample compression schemes and statistical learning, which has been mostly investigated within the framework of binary classification. The central theme of this w…

Binary ClassificationLearning Theory

Supervised learning through the lens of compression

2016-12-01 · NeurIPS 2016 12 · Ofir David, Shay Moran, Amir Yehudayoff

This work continues the study of the relationship between sample compression schemes and statistical learning, which has been mostly investigated within the framework of binary classification. We first extend the investi…

Binary Classification

Compressibility Measures for Affinely Singular Random Vectors

2020-01-12 · Mohammad-Amin Charusaie, Arash Amini, Stefano Rini

There are several ways to measure the compressibility of a random measure; they include general approaches such as using the rate-distortion curve, as well as more specific notions, such as the Renyi information dimensio…

Compressibility Loss for Neural Network Weights

2019-05-03 · Caglar Aytekin, Francesco Cricri, Emre Aksu

In this paper we apply a compressibility loss that enables learning highly compressible neural network weights. The loss was previously proposed as a measure of negated sparsity of a signal, yet in this paper we show tha…