English
Related papers

Related papers: Sample Compression Unleashed: New Generalization B…

200 papers

The effectiveness of non-parametric, kernel-based methods for function estimation comes at the price of high computational complexity, which hinders their applicability in adaptive, model-based control. Motivated by approximation techniques…

Statistics Theory · Mathematics 2023-03-17 Anna Scampicchio , Elena Arcari , Melanie N. Zeilinger

Sequential data is being generated at an unprecedented pace in various forms, including text and genomic data. This creates the need for efficient compression mechanisms to enable better storage, transmission and processing of such data. To…

Computation and Language · Computer Science 2018-11-21 Mohit Goyal , Kedar Tatwawadi , Shubham Chandak , Idoia Ochoa

Generalization under distribution shift remains a core challenge in modern machine learning, yet existing learning bound theory is limited to narrow, idealized settings and is non-estimable from samples. In this paper, we bridge the gap…

Machine Learning · Statistics 2025-08-25 Hongbo Chen , Li Charlie Xia

The impressive growth of data throughput in optical microscopy has triggered a widespread use of supervised learning (SL) models running on compressed image datasets for efficient automated analysis. However, since lossy image compression…

This note presents a simple way to add a count (or quantile) constraint to a regression neural net, such that given $n$ samples in the training set it guarantees that the prediction of $m<n$ samples will be larger than the actual value (the…

Machine Learning · Computer Science 2020-12-29 Dvir Ben Or , Michael Kolomenkin , Gil Shabat

Model Compression has drawn much attention within the deep learning community recently. Compressing a dense neural network offers many advantages including lower computation cost, deployability to devices of limited storage and memories,…

Machine Learning · Computer Science 2024-11-04 Diptarka Saha , Zihe Liu , Feng Liang

We introduce a probability distribution, combined with an efficient sampling algorithm, for weights and biases of fully-connected neural networks. In a supervised learning context, no iterative optimization or gradient computations of…

Machine Learning · Computer Science 2023-11-14 Erik Lien Bolager , Iryna Burak , Chinmay Datar , Qing Sun , Felix Dietrich

A new framework is introduced for examining and evaluating the fundamental limits of lossless data compression, that emphasizes genuinely non-asymptotic results. The {\em sample complexity} of compressing a given source is defined as the…

Information Theory · Computer Science 2026-04-16 Terence Viaud , Ioannis Kontoyiannis

Understanding generalization in modern machine learning settings has been one of the major challenges in statistical learning theory. In this context, recent years have witnessed the development of various generalization bounds suggesting…

Machine Learning · Statistics 2022-07-01 Milad Sefidgaran , Amin Gohari , Gaël Richard , Umut Şimşekli

We give improved constants for data dependent and variance sensitive confidence bounds, called empirical Bernstein bounds, and extend these inequalities to hold uniformly over classes of functionswhose growth function is polynomial in the…

Machine Learning · Statistics 2009-07-23 Andreas Maurer , Massimiliano Pontil

We study the fundamental problem of learning an unknown object from data using a prescribed model class. We introduce a unified framework that accommodates objects in arbitrary Hilbert spaces, general (possibly vector-valued) random linear…

Machine Learning · Computer Science 2026-03-09 Ben Adcock , Juan M. Cardenas , Nick Dexter

Language prediction is constrained by informational entropy intrinsic to language, such that there exists a limit to how accurate any language model can become and equivalently a lower bound to language compression. The most efficient…

Computation and Language · Computer Science 2025-11-14 Benjamin L. Badger , Matthew Neligeorge

This paper presents a theoretical analysis of sample selection bias correction. The sample bias correction technique commonly used in machine learning consists of reweighting the cost of an error on each training point of a biased sample to…

Machine Learning · Computer Science 2008-12-18 Corinna Cortes , Mehryar Mohri , Michael Riley , Afshin Rostamizadeh

Sentence compression reduces the length of text by removing non-essential content while preserving important facts and grammaticality. Unsupervised objective driven methods for sentence compression can be used to create customized models…

Computation and Language · Computer Science 2022-05-18 Demian Gholipour Ghalandari , Chris Hokamp , Georgiana Ifrim

This article studies the achievable guarantees on the error rates of certain learning algorithms, with particular focus on refining logarithmic factors. Many of the results are based on a general technique for obtaining bounds on the error…

Machine Learning · Computer Science 2016-09-13 Steve Hanneke

Compression and generalization are fundamentally related through Solomonoff induction and the minimum description length principle (MDL), which predict that simpler models generalize better when data arises from low-complexity…

Machine Learning · Computer Science 2026-05-14 Lukas Silvester Barth , Paulo von Petersenn

We propose a method for specializing deep detectors and trackers to restricted settings. Our approach is designed with the following goals in mind: (a) Improving accuracy in restricted domains; (b) preventing overfitting to new domains and…

Computer Vision and Pattern Recognition · Computer Science 2019-09-26 Dotan Kaufman , Koby Bibas , Eran Borenstein , Michael Chertok , Tal Hassner

A learned generative model often produces biased statistics relative to the underlying data distribution. A standard technique to correct this bias is importance sampling, where samples from the model are weighted by the likelihood ratio…

Machine Learning · Statistics 2019-11-05 Aditya Grover , Jiaming Song , Alekh Agarwal , Kenneth Tran , Ashish Kapoor , Eric Horvitz , Stefano Ermon

Tokenization is a hardcoded compression step which remains in the training pipeline of Large Language Models (LLMs), despite a general trend towards architectures becoming increasingly end-to-end. Prior work has shown promising results at…

Machine Learning · Computer Science 2026-02-17 Sam Dauncey , Roger Wattenhofer

The goal of machine learning is to find models that minimize prediction error on data that has not yet been seen. Its operational paradigm assumes access to a dataset $S$ and articulates a scheme for evaluating how well a given model…

Machine Learning · Computer Science 2026-04-22 Maxim Raginsky , Benjamin Recht