English
Related papers

Related papers: Minimum Description Length codes are critical

200 papers

Machine learning (ML) has been well applied to studying equilibrium phase transition models, by accurately predicating critical thresholds and some critical exponents. Difficulty will be raised, however, for integrating ML into…

Statistical Mechanics · Physics 2024-02-27 Jianmin Shen , Wei Li , Shengfeng Deng , Tao Zhang

The principle of Maximal Coding Rate Reduction (MCR$^2$) has recently been proposed as a training objective for learning discriminative low-dimensional structures intrinsic to high-dimensional data to allow for more robust training than…

Machine Learning · Computer Science 2022-04-04 Christina Baek , Ziyang Wu , Kwan Ho Ryan Chan , Tianjiao Ding , Yi Ma , Benjamin D. Haeffele

Conserved dynamical systems are generally considered to be critical. We study a class of critical routing models, equivalent to random maps, which can be solved rigorously in the thermodynamic limit. The information flow is conserved for…

Adaptation and Self-Organizing Systems · Physics 2013-01-10 Dimitrije Markovic , Andre Schuelein , Claudius Gros

Linear computation coding is concerned with the compression of multidimensional linear functions, i.e. with reducing the computational effort of multiplying an arbitrary vector to an arbitrary, but known, constant matrix. This paper…

Information Theory · Computer Science 2025-07-02 Hans Rosenberger , Johanna S. Fröhlich , Ali Bereyhi , Ralf R. Müller

We identify and analyze a surprising phenomenon of Latent Diffusion Models (LDMs) where the final steps of the diffusion can degrade sample quality. In contrast to conventional arguments that justify early stopping for numerical stability,…

Machine Learning · Statistics 2026-03-03 Yu-Han Wu , Quentin Berthet , Gérard Biau , Claire Boyer , Romuald Elie , Pierre Marion

A new approach to data compression is developed and applied to multimedia content. This method separates messages into components suitable for both lossless coding and 'lossy' or statistical coding techniques, compressing complex objects by…

Information Theory · Computer Science 2011-12-26 John Scoville

We consider the fundamental problem of inferring the causal direction between two univariate numeric random variables $X$ and $Y$ from observational data. The two-variable case is especially difficult to solve since it is not possible to…

Machine Learning · Statistics 2018-08-23 Alexander Marx , Jilles Vreeken

Solomonoff's general theory of inference and the Minimum Description Length principle formalize Occam's razor, and hold that a good model of data is a model that is good at losslessly compressing the data, including the cost of describing…

Machine Learning · Computer Science 2019-01-29 Léonard Blier , Yann Ollivier

Identifying phase transitions and classifying phases of matter is central to understanding the properties and behavior of a broad range of material systems. In recent years, machine-learning (ML) techniques have been successfully applied to…

Disordered Systems and Neural Networks · Physics 2023-06-23 Julian Arnold , Frank Schäfer

A fundamental problem associated with the task of network reconstruction from dynamical or behavioral data consists in determining the most appropriate model complexity in a manner that prevents overfitting, and produces an inferred network…

Machine Learning · Statistics 2025-03-24 Tiago P. Peixoto

We argue that diffusion models' success in modeling complex distributions is, for the most part, coming from their input conditioning. This paper investigates the representation used to condition diffusion models from the perspective that…

Computer Vision and Pattern Recognition · Computer Science 2026-01-07 Samuel Lavoie , Michael Noukhovitch , Aaron Courville

Generalized linear models (GLMs) arise in high-dimensional machine learning, statistics, communications and signal processing. In this paper we analyze GLMs when the data matrix is random, as relevant in problems such as compressed sensing,…

Information Theory · Computer Science 2019-04-01 Jean Barbier , Florent Krzakala , Nicolas Macris , Léo Miolane , Lenka Zdeborová

In-context learning has established itself as an important learning paradigm for Large Language Models (LLMs). In this paper, we demonstrate that LLMs can learn encoding keys in-context and perform analysis directly on encoded…

Computation and Language · Computer Science 2026-04-16 Andresa Rodrigues de Campos , David Lee , Imry Kissos , Piyush Paritosh

Machine learning (ML) can process large sets of data generated from complex systems, which is ideal for classification tasks as often appeared in critical phenomena. Meanwhile ML techniques have been found effective in detecting critical…

Computational Physics · Physics 2024-05-07 Shen Jianmin , Wang Shanshan , Li Wei , Xu Dian , Yang Yuxiang , Wang Yanyang , Gao Feng , Zhu Yueying , Tuo Kui

We introduce a method to determine if a certain capability helps to achieve an accurate model of given data. We view labels as being generated from the inputs by a program composed of subroutines with different capabilities, and we posit…

Machine Learning · Computer Science 2021-03-08 Ethan Perez , Douwe Kiela , Kyunghyun Cho

Graph pooling compresses graphs and summarises their topological properties and features in a vectorial representation. It is an essential part of deep graph representation learning and is indispensable in graph-level tasks like…

Machine Learning · Computer Science 2025-05-16 Jan von Pichowski , Christopher Blöcker , Ingo Scholtes

This paper studies the theory of linear analog error correction coding. Since classical concepts of minimum Hamming distance and minimum Euclidean distance fail in the analog context, a new metric, termed the "minimum (squared Euclidean)…

Information Theory · Computer Science 2011-05-10 Kai Xie , Jing , Li

The most basic assumption used in statistical learning theory is that training data and test data are drawn from the same underlying distribution. Unfortunately, in many applications, the "in-domain" test data is drawn from a distribution…

Machine Learning · Computer Science 2011-09-30 H. Daume , D. Marcu

We study the problem of zero-delay coding for the transmission of a Markov source over a noisy channel with feedback and present a reinforcement learning solution which is guaranteed to achieve near-optimality. To this end, we formulate the…

Optimization and Control · Mathematics 2025-10-07 Liam Cregg , Fady Alajaji , Serdar Yuksel

During the finetuning stage of text generation tasks, standard cross-entropy loss treats all tokens equally. This can lead models to overemphasize high-frequency, low-information tokens, neglecting lower-frequency tokens crucial for…

Computation and Language · Computer Science 2025-06-10 Jintian Shao
‹ Prev 1 4 5 6 7 8 10 Next ›