paper-with-me

Papers

Maximum Multiscale Entropy and Neural Network Regularization

2020-06-25 · Amir R. Asadi, Emmanuel Abbe

A well-known result across information theory, machine learning, and statistical physics shows that the maximum entropy distribution under a mean constraint has an exponential form called the Gibbs-Boltzmann distribution. This is used for instance in density estimation or to achieve excess risk bounds derived from single-scale entropy regularizers (Xu-Raginsky '17). This paper investigates a generalization of these results to a multiscale setting. We present different ways of generalizing the maximum entropy result by incorporating the notion of scale. For different entropies and arbitrary scale transformations, it is shown that the distribution maximizing a multiscale entropy is characterized by a procedure which has an analogy to the renormalization group procedure in statistical physics. For the case of decimation transformation, it is further shown that this distribution is Gaussian whenever the optimal single-scale distribution is Gaussian. This is then applied to neural networks, and it is shown that in a teacher-student scenario, the multiscale Gibbs posterior can achieve a smaller excess risk than the single-scale Gibbs posterior.

📄 PDF Abstract BibTeX arXiv:2006.14614

Code (0)

등록된 구현이 없습니다.

Tasks

Density Estimation

Similar Papers 제목 키워드 기반

ELEMENT: Episodic and Lifelong Exploration via Maximum Entropy

2024-12-05 · Hongming Li, Shujian Yu, Bin Liu, Jose C. Principe

This paper proposes \emph{Episodic and Lifelong Exploration via Maximum ENTropy} (ELEMENT), a novel, multiscale, intrinsically motivated reinforcement learning (RL) framework that is able to explore environments without …

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Multiscale Sparse Microcanonical Models

2018-01-06 · Joan Bruna, Stephane Mallat

We study approximations of non-Gaussian stationary processes having long range correlations with microcanonical models. These models are conditioned by the empirical value of an energy vector, evaluated on a single reali…

Gaussian ProcessesPoint ProcessesTexture Synthesis

Maximum Entropy Regularization and Chinese Text Recognition

2020-07-09 · Changxu Cheng, Wuheng Xu, Xiang Bai, Bin Feng 외

Chinese text recognition is more challenging than Latin text due to the large amount of fine-grained Chinese characters and the great imbalance over classes, which causes a serious overfitting problem. We propose to appl…

Fine-Grained Image Classificationimage-classificationImage Classification

Failure Modes of Maximum Entropy RLHF

2025-09-24 · Ömer Veysel Çağatan, Barış Akgün arxiv

In this paper, we show that Simple Preference Optimization (SimPO) can be derived as Maximum Entropy Reinforcement Learning, providing a theoretical foundation for this reference-free method. Motivated by SimPO's strong …

Reinforcement Learning

MGD: Moment Guided Diffusion for Maximum Entropy Generation

2026-02-19 · Etienne Lempereur, Nathanaël Cuvelle--Magar, Florentin Coeurdoux, Stéphane Mallat 외 arxiv

Generating samples from limited information is a fundamental problem across scientific domains. Classical maximum entropy methods provide principled uncertainty quantification from moment constraints but require sampling…