English
Related papers

Related papers: Discrete Layered Entropy, Conditional Compression …

200 papers

Large language models (LLMs) achieve remarkable generative performance, yet their output quality is dependent on the decoding strategy. While sampling-based methods (e.g., top-k, nucleus) and search-and-select based methods (e.g., beam…

Machine Learning · Computer Science 2026-05-12 Benjamin Patrick Evans , Sumitra Ganesh , Leo Ardon

Reasoning models often outperform smaller models but at 3--5$\times$ higher cost and added latency. We present entropy-guided refinement: a lightweight, test-time loop that uses token-level uncertainty to trigger a single, targeted…

Artificial Intelligence · Computer Science 2025-09-03 Andrew G. A. Correa , Ana C. H de Matos

Neural networks have dramatically increased our capacity to learn from large, high-dimensional datasets across innumerable disciplines. However, their decisions are not easily interpretable, their computational costs are high, and building…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Mackenzie J. Meni , Ryan T. White , Michael Mayo , Kevin Pilkiewicz

As conventional communication systems based on classic information theory have closely approached the limits of Shannon channel capacity, semantic communication has been recognized as a key enabling technology for the further improvement of…

Information Theory · Computer Science 2023-06-06 Jiancheng Tang , Qianqian Yang , Zhaoyang Zhang

We use entropy numbers in combination with the polynomial method to derive a new general lower bound for the n-th minimal error in the quantum setting of information-based complexity. As an application, we improve some lower bounds on…

Quantum Physics · Physics 2007-05-23 Stefan Heinrich

This paper investigates the problem of variable-length lossy source coding allowing a positive excess distortion probability and an overflow probability of codeword lengths. Novel one-shot achievability and converse bounds of the optimal…

Information Theory · Computer Science 2018-12-17 Shota Saito , Hideki Yagi , Toshiyasu Matsushima

A new nonparametric model of maximum-entropy (MaxEnt) copula density function is proposed, which offers the following advantages: (i) it is valid for mixed random vector. By `mixed' we mean the method works for any combination of discrete…

Statistics Theory · Mathematics 2022-08-23 Subhadeep , Mukhopadhyay

Shannon Entropy has been extensively used for characterizing complexity of time series arising from chaotic dynamical systems and stochastic processes such as Markov chains. However, for short and noisy time series, Shannon entropy performs…

Chaotic Dynamics · Physics 2016-12-08 Nithin Nagaraj , Karthi Balasubramanian

This work proposes a new computational framework for learning a structured generative model for real-world datasets. In particular, we propose to learn a closed-loop transcription between a multi-class multi-dimensional data distribution…

Computer Vision and Pattern Recognition · Computer Science 2022-04-06 Xili Dai , Shengbang Tong , Mingyang Li , Ziyang Wu , Michael Psenka , Kwan Ho Ryan Chan , Pengyuan Zhai , Yaodong Yu , Xiaojun Yuan , Heung Yeung Shum , Yi Ma

In this paper we study the problem of computing max-entropy distributions over a discrete set of objects subject to observed marginals. Interest in such distributions arises due to their applicability in areas such as statistical physics,…

Data Structures and Algorithms · Computer Science 2013-05-02 Mohit Singh , Nisheeth K. Vishnoi

In many real-world applications, data is not collected as one batch, but sequentially over time, and often it is not possible or desirable to wait until the data is completely gathered before analyzing it. Thus, we propose a framework to…

Machine Learning · Statistics 2018-03-09 Elizabeth Hou , Alfred O. Hero

Bayesian optimal experimental design provides a principled framework for selecting experimental settings that maximize obtained information. In this work, we focus on estimating the expected information gain in the setting where the…

Machine Learning · Statistics 2025-10-02 Chuntao Chen , Tapio Helin , Nuutti Hyvönen , Yuya Suzuki

Predictive inference requires balancing statistical accuracy against informational complexity, yet the choice of complexity measure is usually imposed rather than derived. We treat econometric objects as predictive rules, mappings from…

Statistics Theory · Mathematics 2026-02-16 Nicholas G. Polson , Daniel Zantedeschi

The theorem of Shannon-McMillan-Breiman states that for every generating partition on an ergodic system, the exponential decay rate of the measure of cylinder sets equals the metric entropy almost everywhere (provided the entropy is…

Dynamical Systems · Mathematics 2009-03-10 Nicolai T A Haydn

Post-processing of the raw bits produced by a true random number generator (TRNG) is always necessary when the entropy per bit is insufficient for security applications. In this paper, we derive a tight bound on the output min-entropy of…

Cryptography and Security · Computer Science 2024-06-25 Miloš Grujić , Ingrid Verbauwhede

I consider the effect of a finite sample size on the entropy of a sample of independent events. I propose formula for entropy which satisfies Shannon's axioms, and which reduces to Shannon's entropy when sample size is infinite. I discuss…

Information Theory · Computer Science 2015-04-08 Sergei Viznyuk

In the present work we investigate phase correlations by recourse to the Shannon entropy. Using theoretical arguments we show that the entropy provides an accurate measure of phase correlations in any dynamical system, in particular when…

Chaotic Dynamics · Physics 2019-10-24 P. M. Cincotta , C. M. Giordano

This paper investigates approximation-theoretic aspects of the in-context learning capability of the transformers in representing a family of noisy linear dynamical systems. Our first theoretical result establishes an upper bound on the…

Machine Learning · Computer Science 2025-10-22 Frank Cole , Yuxuan Zhao , Yulong Lu , Tianhao Zhang

Given a sequence composed of a limit number of characters, we try to "read" it as a "text". This involves to segment the sequence into "words". The difficulty is to distinguish good segmentation from enormous number of random ones.Aiming at…

Biological Physics · Physics 2009-11-06 Bin Wang

We introduce a method for quantifying the inherent unpredictability of a continuous-valued time series via an extension of the differential Shannon entropy rate. Our extension, the specific entropy rate, quantifies the amount of predictive…

Machine Learning · Computer Science 2016-06-09 David Darmon