English
Related papers

Related papers: Rethinking GSPO: The Perplexity-Entropy Equivalenc…

200 papers

Recent advances in large language models (LLMs) have accelerated progress toward artificial general intelligence, with inference-time scaling emerging as a key technique. Contemporary approaches leverage either sequential reasoning…

Computation and Language · Computer Science 2025-07-10 Zenan Xu , Zexuan Qiu , Guanhua Huang , Kun Li , Siheng Li , Chenchen Zhang , Kejiao Li , Qi Yi , Yuhao Jiang , Bo Zhou , Fengzong Lian , Zhanhui Kang

We study the permutation complexity of finite-state stationary stochastic processes based on a duality between values and orderings between values. First, we establish a duality between the set of all words of a fixed length and the set of…

Chaotic Dynamics · Physics 2011-12-13 Taichi Haruna , Kohei Nakajima

This paper establishes risk convergence and asymptotic weight matrix alignment --- a form of implicit regularization --- of gradient flow and gradient descent when applied to deep linear networks on linearly separable data. In more detail,…

Machine Learning · Computer Science 2019-02-26 Ziwei Ji , Matus Telgarsky

We introduce Entropy-Guided Sequence Weighting (EGSW), a novel approach that enhances the exploration-exploitation tradeoff by dynamically assigning weights to generated outputs based on their advantage and entropy for Reinforcement…

Machine Learning · Computer Science 2025-04-01 Abdullah Vanlioglu

GRPO is a standard approach to endowing pretrained LLMs with reasoning capabilities. It estimates the advantage of an outcome from a group of $K$ outcomes, and promotes those with positive advantages inside a trust region. Since GRPO…

Machine Learning · Computer Science 2026-02-02 Wenzheng Zhang , Karl Stratos

As a part of the construction of an information theory based on general probabilistic theories, we propose and investigate the several distinguishability measures and "entropies" in general probabilistic theories. As their applications,…

Quantum Physics · Physics 2015-05-14 Gen Kimura , Koji Nuida , Hideki Imai

We revisit test-time scaling for language model reasoning and ask a fundamental question: at equal token budget and compute, is it better to run multiple independent chains in parallel, or to run fewer chains that iteratively refine through…

Machine Learning · Computer Science 2025-11-05 Aman Sharma , Paras Chopra

Mechanistic interpretability aims to break models into meaningful parts; verifying that two such parts implement the same computation is a prerequisite. Existing similarity measures evaluate either empirical behaviour, leaving them blind to…

Machine Learning · Computer Science 2026-05-15 ML Nissen Gonzalez , Melwina Albuquerque , Laurence Wroe , Jacob Meyer Cohen , Logan Riggs Smith , Thomas Dooms

SWE-bench has emerged as the premier benchmark for evaluating Large Language Models on complex software engineering tasks. While these capabilities are fundamentally acquired during the mid-training phase and subsequently elicited during…

Machine Learning · Computer Science 2026-05-29 Yueyang Wang , Jiawei Fu , Baolong Bi , Xili Wang , Xiaoqing Liu

We study how the Shannon entropy of sequences produced by an information source converges to the source's entropy rate. We synthesize several phenomenological approaches to applying information theoretic measures of randomness and memory to…

Statistical Mechanics · Physics 2007-05-23 James P. Crutchfield , David P. Feldman

We show that the natural scaling of measurement for a particular problem defines the most likely probability distribution of observations taken from that measurement scale. Our approach extends the method of maximum entropy to use…

Quantitative Methods · Quantitative Biology 2010-03-02 Steven A. Frank , D. Eric Smith

We examine a class of deep learning models with a tractable method to compute information-theoretic quantities. Our contributions are three-fold: (i) We show how entropies and mutual informations can be derived from heuristic statistical…

Machine Learning · Computer Science 2020-01-22 Marylou Gabrié , Andre Manoel , Clément Luneau , Jean Barbier , Nicolas Macris , Florent Krzakala , Lenka Zdeborová

Reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving the reasoning ability of large language models. However, widely used RLVR algorithms, such as GRPO, often suffer from entropy collapse,…

Machine Learning · Computer Science 2026-05-13 Huimin Xu , Shuai Zhao , Xiaobao Wu , Anh Tuan Luu

Entropy serves as a critical metric for measuring the diversity of outputs generated by large language models (LLMs), providing valuable insights into their exploration capabilities. While recent studies increasingly focus on monitoring and…

Machine Learning · Computer Science 2026-02-04 Shumin Wang , Yuexiang Xie , Wenhao Zhang , Yuchang Sun , Yanxi Chen , Yaliang Li , Yanyong Zhang

Surprisal theory posits that the cognitive effort required to comprehend a word is determined by its contextual predictability, quantified as surprisal. Traditionally, surprisal theory treats words as distinct entities, overlooking any…

Computation and Language · Computer Science 2024-10-24 Clara Meister , Mario Giulianelli , Tiago Pimentel

Stimulated by the need of describing useful notions related to information measures, we introduce the `pdf-related distributions'. These are defined in terms of transformation of absolutely continuous random variables through their own…

Probability · Mathematics 2024-05-02 Antonio Di Crescenzo , Luca Paolillo , Alfonso Suarez-Llorens

The precise one-shot characterisation of operational tasks in classical and quantum information theory relies on different forms of smooth entropic quantities. A particularly important connection is between the hypothesis testing relative…

Quantum Physics · Physics 2026-04-29 Bartosz Regula , Ludovico Lami , Nilanjana Datta

Attributions aim to identify input pixels that are relevant to the decision-making process. A popular approach involves using modified backpropagation (BP) rules to reverse decisions, which improves interpretability compared to the original…

Machine Learning · Computer Science 2025-03-17 Guanhua Zheng , Jitao Sang , Changsheng Xu

To improve Multi-step Mathematical Reasoning (MsMR) of Large Language Models (LLMs), it is crucial to obtain scalable supervision from the corpus by automatically critiquing mistakes in the reasoning process of MsMR and rendering a final…

Computation and Language · Computer Science 2025-11-14 Changyuan Tian , Zhicong Lu , Shuang Qian , Nayu Liu , Peiguang Li , Li Jin , Leiyi Hu , Zhizhao Zeng , Sirui Wang , Ke Zeng , Zhi Guo

We propose a new type of entropic descriptor that is able to quantify the statistical complexity (a measure of complex behaviour) by taking simultaneously into account the average departures of a system's entropy S from both its maximum…

Statistical Mechanics · Physics 2015-05-13 R. Piasecki , A. Plastino
‹ Prev 1 4 5 6 7 8 10 Next ›