English
Related papers

Related papers: Empirical Lossless Compression Bound of a Data Seq…

200 papers

Finding methods for making generalizable predictions is a fundamental problem of machine learning. By looking into similarities between the prediction problem for unknown data and the lossless compression we have found an approach that…

Machine Learning · Computer Science 2020-06-24 Michael Tetelman

If the log likelihood is approximately quadratic with constant Hessian, then the maximum likelihood estimator (MLE) is approximately normally distributed. No other assumptions are required. We do not need independent and identically…

Statistics Theory · Mathematics 2012-07-06 Charles J. Geyer

We present new lower and upper bounds for the compression rate of binary prefix codes optimized over memoryless sources according to two related exponential codeword length objectives. The objectives explored here are exponential-average…

Information Theory · Computer Science 2011-05-03 Michael B. Baer

Consider a general quantum stochastic source that emits at discrete time steps quantum pure states which are chosen from a finite alphabet according to some probability distribution which may depend on the whole history. Also, fix two…

Quantum Physics · Physics 2024-12-05 George Androulakis , Rabins Wosti

The aim of this note is to state a couple of general results about the properties of the penalized maximum likelihood estimators (pMLE) and of the posterior distribution for parametric models in a non-asymptotic setup and for possibly large…

Statistics Theory · Mathematics 2022-12-13 Vladimir Spokoiny

We propose a general framework for neural network compression that is motivated by the Minimum Description Length (MDL) principle. For that we first derive an expression for the entropy of a neural network, which measures its complexity…

Machine Learning · Computer Science 2018-12-20 Simon Wiedemann , Arturo Marban , Klaus-Robert Müller , Wojciech Samek

We study the problem of learning multivariate log-concave densities with respect to a global loss function. We obtain the first upper bound on the sample complexity of the maximum likelihood estimator (MLE) for a log-concave density on…

Statistics Theory · Mathematics 2018-12-06 Timothy Carpenter , Ilias Diakonikolas , Anastasios Sidiropoulos , Alistair Stewart

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

We study perfect error-correcting codes in $\mathbb{Z}^n$ for the symmetric limited-magnitude error channel, where at most $e$ coordinates of an integer vector may be altered by a value whose magnitude is at most $s$. Geometrically, such…

Information Theory · Computer Science 2026-01-21 Zhihao Guan , Hengjia Wei

The classical asymptotic theory for parametric $M$-estimators guarantees that, in the limit of infinite sample size, the excess risk has a chi-square type distribution, even in the misspecified case. We demonstrate how self-concordance of…

Statistics Theory · Mathematics 2020-12-01 Dmitrii Ostrovskii , Francis Bach

Universal compression of patterns of sequences generated by independently identically distributed (i.i.d.) sources with unknown, possibly large, alphabets is investigated. A pattern is a sequence of indices that contains all consecutive…

Information Theory · Computer Science 2016-11-17 Gil I. Shamir

Consider the problem of predicting the next symbol given a sample path of length n, whose joint distribution belongs to a distribution class that may have long-term memory. The goal is to compete with the conditional predictor that knows…

Statistics Theory · Mathematics 2024-04-25 Yanjun Han , Tianze Jiang , Yihong Wu

The asymptotic normality of the Maximum Likelihood Estimator (MLE) is a cornerstone of statistical theory. In the present paper, we provide sharp explicit upper bounds on Zolotarev-type distances between the exact, unknown distribution of…

Statistics Theory · Mathematics 2016-04-19 Andreas Anastasiou , Christophe Ley

In this paper, we propose {\em distributed network compression via memory}. We consider two spatially separated sources with correlated unknown source parameters. We wish to study the universal compression of a sequence of length $n$ from…

Information Theory · Computer Science 2012-10-09 Ahmad Beirami , Faramarz Fekri

Compression refers to encoding data using bits, so that the representation uses as few bits as possible. Compression could be lossless: i.e. encoded data can be recovered exactly from its representation) or lossy where the data is…

Information Theory · Computer Science 2012-10-19 Narayana Santhanam , Dharmendra Modha

Grammar compression is a general compression framework in which a string $T$ of length $N$ is represented as a context-free grammar of size $n$ whose language contains only $T$. In this paper, we focus on studying the limitations of…

Data Structures and Algorithms · Computer Science 2024-09-24 Rajat De , Dominik Kempa

Shannon's entropy is a clear lower bound for statistical compression. The situation is not so well understood for dictionary-based compression. A plausible lower bound is $b$, the least number of phrases of a general bidirectional parse of…

Data Structures and Algorithms · Computer Science 2019-10-29 Gonzalo Navarro , Carlos Ochoa , Nicola Prezza

Model selection is central to statistics, and many learning problems can be formulated as model selection problems. In this paper, we treat the problem of selecting a maximum entropy model given various feature subsets and their moments, as…

Information Theory · Computer Science 2013-11-28 Gaurav Pandey , Ambedkar Dukkipati

We present herein a scheme by which to accurately evaluate the error exponents of a lossy data compression problem, which characterize average probabilities over a code ensemble of compression failure and success above or below a critical…

Statistical Mechanics · Physics 2007-05-23 Tadaaki Hosaka , Yoshiyuki Kabashima

Suppose $\widehat\theta_n$ is a strongly consistent estimator for $\theta_0$ in some i.i.d. situation. Let $N_\varepsilon$ and $Q_\varepsilon$ be respectively the last $n$ and the total number of $n$ for which $\widehat\theta_n$ is at least…

Statistics Theory · Mathematics 2026-03-11 Nils Lid Hjort , Grete Fenstad