English
Related papers

Related papers: Upper Bound on Normalized Maximum Likelihood Codes…

200 papers

Clustering is a widely used technique with a long and rich history in a variety of areas. However, most existing algorithms do not scale well to large datasets, or are missing theoretical guarantees of convergence. This paper introduces a…

Machine Learning · Statistics 2024-10-16 Yijia Zhou , Kyle A. Gallivan , Adrian Barbu

Why do larger language models generalize better? To investigate this question, we develop generalization bounds on the pretraining objective of large language models (LLMs) in the compute-optimal regime, as described by the Chinchilla…

Machine Learning · Computer Science 2025-04-22 Marc Finzi , Sanyam Kapoor , Diego Granziol , Anming Gu , Christopher De Sa , J. Zico Kolter , Andrew Gordon Wilson

In this work, we study the generalization capability of algorithms from an information-theoretic perspective. It has been shown that the expected generalization error of an algorithm is bounded from above by a function of the relative…

Information Theory · Computer Science 2021-10-27 Borja Rodríguez-Gálvez , Germán Bassi , Mikael Skoglund

We provide two fundamental results on the population (infinite-sample) likelihood function of Gaussian mixture models with $M \geq 3$ components. Our first main result shows that the population likelihood function has bad local maxima even…

Machine Learning · Statistics 2016-09-06 Chi Jin , Yuchen Zhang , Sivaraman Balakrishnan , Martin J. Wainwright , Michael Jordan

Generalized linear mixed models (GLMM) are used for inference and prediction in a wide range of different applications providing a powerful scientific tool. An increasing number of sources of data are becoming available, introducing a…

Computation · Statistics 2019-03-19 Aliaksandr Hubin , Geir Storvik

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…

Machine Learning · Computer Science 2020-06-26 Amir R. Asadi , Emmanuel Abbe

New upper and lower bounds for the error probability over an erasure channel are provided, making use of Wei's generalized weights, hierarchy and spectra. In many situations the upper and lower bounds coincide and this allows improvement of…

Information Theory · Computer Science 2014-07-18 Leandro Cruvinel Lemes , Marcelo Firer

We consider linear rank-metric codes in $\mathbb F_{q^m}^n$. We show that the properties of being MRD (maximum rank distance) and non-Gabidulin are generic over the algebraic closure of the underlying field, which implies that over a large…

Information Theory · Computer Science 2018-03-13 Alessandro Neri , Anna-Lena Horlemann-Trautmann , Tovohery Randrianarisoa , Joachim Rosenthal

We study asymptotic lower and upper bounds for the sizes of constant dimension codes with respect to the subspace or injection distance, which is used in random linear network coding. In this context we review known upper bounds and show…

Combinatorics · Mathematics 2017-12-06 Daniel Heinlein , Sascha Kurz

We consider maximum likelihood estimation of finite mixture of uniform distributions. We prove that maximum likelihood estimator is strongly consistent, if the scale parameters of the component uniform distributions are restricted from…

Statistics Theory · Mathematics 2007-06-13 Kentaro Tanaka , Akimichi Takemura

We derive a linear programming bound on the maximum cardinality of error-correcting codes in the sum-rank metric. Based on computational experiments on relatively small instances, we observe that the obtained bounds outperform all…

Combinatorics · Mathematics 2024-06-25 Aida Abiad , Alexander L. Gavrilyuk , Antonina P. Khramova , Ilia Ponomarenko

We study the estimation error of constrained M-estimators, and derive explicit upper bounds on the expected estimation error determined by the Gaussian width of the constraint set. Both of the cases where the true parameter is on the…

Statistics Theory · Mathematics 2015-06-29 Yen-Huan Li , Ya-Ping Hsieh , Nissim Zerbib , Volkan Cevher

An information-theoretic upper bound on the generalization error of supervised learning algorithms is derived. The bound is constructed in terms of the mutual information between each individual training sample and the output of the…

Machine Learning · Computer Science 2020-08-06 Yuheng Bu , Shaofeng Zou , Venugopal V. Veeravalli

We consider the problem of universal decoding for arbitrary unknown channels in the random coding regime. For a given random coding distribution and a given class of metric decoders, we propose a generic universal decoder whose average…

Information Theory · Computer Science 2016-11-17 Neri Merhav

This paper investigates and bounds the expected solution quality of combinatorial optimization problems when feasible solutions are chosen at random. Loose general bounds are discovered, as well as families of combinatorial optimization…

Data Structures and Algorithms · Computer Science 2014-02-04 Evan A. Sultanik

Generalized Linear Model (or GLM) extends the ordinary linear regression by linking the mean of the response variable to covariates through appropriate link functions. GLM is widely used in the analysis of datasets arising from diverse…

Methodology · Statistics 2026-04-28 Mayukh Choudhury , Debraj Das

Over the last decade, a wave of research has characterized the exact asymptotic risk of many high-dimensional models in the proportional regime. Two foundational results have driven this progress: Gaussian universality, which shows that the…

Statistics Theory · Mathematics 2025-09-10 Matthew Esmaili Mallory , Kevin Han Huang , Morgane Austern

The generalised linear model (GLM) is a very important tool for analysing real data in biology, sociology, agriculture, engineering and many other application domain where the relationship between the response and explanatory variables may…

Methodology · Statistics 2016-07-04 Abhik Ghosh , Ayanendranath Basu

This paper presents a method to calculate the exact average block error probability of some random code ensembles under maximum-likelihood decoding. The proposed method is applicable to various channels and ensembles. The focus is on both…

Information Theory · Computer Science 2022-03-01 Ralf R. Müller

Score based learning (SBL) is a promising approach for learning Bayesian networks in the discrete domain. However, when employing SBL in the continuous domain, one is either forced to move the problem to the discrete domain or use metrics…

Machine Learning · Computer Science 2024-10-30 Borzou Alipourfard , Jean X. Gao
‹ Prev 1 8 9 10 Next ›