English
Related papers

Related papers: Predictability, complexity and learning

200 papers

Forecasting accuracy is bounded by the information available about the future. This paper makes that statement precise using information-theoretic tools. Under logarithmic loss, the expected performance of any probabilistic forecast…

Applications · Statistics 2026-04-01 Peter Maurice Catt

Human language has a distinct systematic structure, where utterances break into individually meaningful words which are combined to form phrases. We show that natural-language-like systematicity arises in codes that are constrained by a…

Computation and Language · Computer Science 2025-11-19 Richard Futrell , Michael Hahn

Can we learn more from data than existed in the generating process itself? Can new and useful information be constructed from merely applying deterministic transformations to existing data? Can the learnable content in data be evaluated…

Machine Learning · Computer Science 2026-03-17 Marc Finzi , Shikai Qiu , Yiding Jiang , Pavel Izmailov , J. Zico Kolter , Andrew Gordon Wilson

We introduce an information theoretic measure of statistical structure, called 'binding information', for sets of random variables, and compare it with several previously proposed measures including excess entropy, Bialek et al.'s…

Statistics Theory · Mathematics 2010-12-10 Samer A. Abdallah , Mark D. Plumbley

Generative models trained on finite data face a fundamental tension: their score-matching or next-token objective converges to the empirical training distribution rather than the population distribution we seek to learn. Using rule-valid…

Machine Learning · Computer Science 2026-05-12 Binxu Wang , Emma Lucia Byrnes Finn , Bingbin Liu

Construction methods for prior densities are investigated from a predictive viewpoint. Predictive densities for future observables are constructed by using observed data. The simultaneous distribution of future observables and observed data…

Statistics Theory · Mathematics 2021-05-27 Fumiyasu Komaki

Predicting the evolution of a large system of units using its structure of interaction is a fundamental problem in complex system theory. And so is the problem of reconstructing the structure of interaction from temporal observations. Here,…

Statistical Mechanics · Physics 2025-02-10 Charles Murphy , Vincent Thibeault , Antoine Allard , Patrick Desrosiers

We use a formal correspondence between thermodynamics and inference, where the number of samples can be thought of as the inverse temperature, to study a quantity called ``learning capacity'' which is a measure of the effective…

Machine Learning · Computer Science 2024-10-22 Daiwei Chen , Wei-Kai Chang , Pratik Chaudhari

Appealing to several multivariate information measures---some familiar, some new here---we analyze the information embedded in discrete-valued stochastic time series. We dissect the uncertainty of a single observation to demonstrate how the…

Information Theory · Computer Science 2015-05-28 Ryan G. James , Christopher J. Ellison , James P. Crutchfield

A measure called Physical Complexity is established and calculated for a population of sequences, based on statistical physics, automata theory, and information theory. It is a measure of the quantity of information in an organism's genome.…

Biological Physics · Physics 2011-12-02 Gerard Briscoe , Philippe De Wilde

Statistical Inference is the process of determining a probability distribution over the space of parameters of a model given a data set. As more data becomes available this probability distribution becomes updated via the application of…

Disordered Systems and Neural Networks · Physics 2022-04-28 David S. Berman , Jonathan J. Heckman , Marc Klinger

Existing work on understanding deep learning often employs measures that compress all data-dependent information into a few numbers. In this work, we adopt a perspective based on the role of individual examples. We introduce a measure of…

Machine Learning · Computer Science 2021-06-21 Robert J. N. Baldock , Hartmut Maennel , Behnam Neyshabur

Many real-world decision processes are modeled by optimization problems whose defining parameters are unknown and must be inferred from observable data. The Predict-Then-Optimize framework uses machine learning models to predict unknown…

Machine Learning · Computer Science 2023-11-23 James Kotary , Vincenzo Di Vito , Jacob Christopher , Pascal Van Hentenryck , Ferdinando Fioretto

Learning is a distinctive feature of intelligent behaviour. High-throughput experimental data and Big Data promise to open new windows on complex systems such as cells, the brain or our societies. Yet, the puzzling success of Artificial…

Machine Learning · Computer Science 2022-05-04 Matteo Marsili , Yasser Roudi

Science consists on conceiving hypotheses, confronting them with empirical evidence, and keeping only hypotheses which have not yet been falsified. Under deductive reasoning they are conceived in view of a theory and confronted with…

Machine Learning · Computer Science 2022-11-04 Diego Marcondes , Adilson Simonis , Junior Barrera

We propose to examine the predictability and the complexity characteristics of the Standard&Poor500 dynamics behaviors in a coarse-grained way using the symbolic dynamics method and under the prism of the Information theory through the…

Statistical Finance · Quantitative Finance 2021-05-11 Geoffrey Ducournau

Despite the increasing prevalence of large language models (LLMs), we still have a limited understanding of how their representational spaces are structured. This limits our ability to interpret how and what they learn or relate them to…

Social learning is defined as the ability of a population to aggregate information, a process which must crucially depend on the mechanisms of social interaction. Consumers choosing which product to buy, or voters deciding which option to…

Physics and Society · Physics 2011-07-12 J. C. González-Avella , V. M. Eguíluz , M. Marsili , F. Vega-Redondo , M. San Miguel

Specifying a Bayesian prior is notoriously difficult for complex models such as neural networks. Reasoning about parameters is made challenging by the high-dimensionality and over-parameterization of the space. Priors that seem benign and…

Machine Learning · Statistics 2020-10-22 Eric Nalisnick , Jonathan Gordon , José Miguel Hernández-Lobato

In the previous papers (Kui\'{c} et al. in Found Phys 42:319-339, 2012; Kui\'{c} in arXiv:1506.02622, 2015), it was demonstrated that applying the principle of maximum information entropy by maximizing the conditional information entropy,…

Statistical Mechanics · Physics 2016-06-14 Domagoj Kuic