paper-with-me

홈 › Papers

Fast and close Shannon entropy approximation

2025-05-20 · Illia Horenko, Davide Bassetti, Lukáš Pospíšil

Shannon entropy (SE) and its quantum mechanical analogue von Neumann entropy are key components in many tools used in physics, information theory, machine learning (ML) and quantum computing. Besides of the significant amounts of SE computations required in these fields, the singularity of the SE gradient is one of the central mathematical reason inducing the high cost, frequently low robustness and slow convergence of such tools. Here we propose the Fast Entropy Approximation (FEA) - a non-singular rational approximation of Shannon entropy and its gradient that achieves a mean absolute error of $10^{-3}$, which is approximately $20$ times lower than comparable state-of-the-art methods. FEA allows around $50\%$ faster computation, requiring only $5$ to $6$ elementary computational operations, as compared to tens of elementary operations behind the fastest entropy computation algorithms with table look-ups, bitshifts, or series approximations. On a set of common benchmarks for the feature selection problem in machine learning, we show that the combined effect of fewer elementary operations, low approximation error, and a non-singular gradient allows significantly better model quality and enables ML feature extraction that is two to three orders of magnitude faster and computationally cheaper when incorporating FEA into AI tools.

📄 PDF Abstract BibTeX arXiv:2505.14234

Code (0)

등록된 구현이 없습니다.

Tasks

feature selection

Methods 이 논문이 사용한 방법론

Feature Selection Feature selection, also known as variable selection, attribute selection or variable subset selection, is the process of selecting a subset of relevant features (variables,…
SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Enforcing KL Regularization in General Tsallis Entropy Reinforcement Learning via Advantage Learning

2022-05-16 · Lingwei Zhu, Zheng Chen, Eiji Uchibe, Takamitsu Matsubara

Maximum Tsallis entropy (MTE) framework in reinforcement learning has gained popularity recently by virtue of its flexible modeling choices including the widely used Shannon entropy and sparse entropy. However, non-Shann…

reinforcement-learningReinforcement Learning (RL)

A Theory on AI Uncertainty Based on Rademacher Complexity and Shannon Entropy

2020-11-19 · Mingyong Zhou

In this paper, we present a theoretical discussion on AI deep learning neural network uncertainty investigation based on the classical Rademacher complexity and Shannon entropy. First it is shown that the classical Radem…

General Classification

Variance of entropy for testing time-varying regimes with an application to meme stocks

2022-11-10 · Andrey Shternshis, Piero Mazzarisi

Shannon entropy is the most common metric to measure the degree of randomness of time series in many fields, ranging from physics and finance to medicine and biology. Real-world systems may be in general non stationary, …

Time SeriesTime Series Analysis

AI Uncertainty Based on Rademacher Complexity and Shannon Entropy

2021-02-12 · Mingyong Zhou

In this paper from communication channel coding perspective we are able to present both a theoretical and practical discussion of AI's uncertainty, capacity and evolution for pattern classification based on the classical…

ClassificationGeneral Classification

A Bayesian Monte-Carlo Uncertainty Model for Assessment of Shear Stress Entropy

2020-01-10 · Amin Kazemian-Kale-Kale, Azadeh Gholami, Mohammad Rezaie-Balf, Amir Mosavi 외

The entropy models have been recently adopted in many studies to evaluate the distribution of the shear stress in circular channels. However, the uncertainty in their predictions and their reliability remains an open que…

Open-Ended Question Answering