English
Related papers

Related papers: Sample Compression Unleashed: New Generalization B…

200 papers

We consider the lossless compression bound of any individual data sequence. If we fit the data by a parametric model, the entropy quantity $nH({\hat \theta}_n)$ obtained by plugging in the maximum likelihood estimate is an underestimate of…

Information Theory · Computer Science 2024-01-23 Lei M Li

A "bigger is better" explosion in the number of parameters in deep neural networks has made it increasingly challenging to make state-of-the-art networks accessible in compute-restricted environments. Compression techniques have taken on…

Computation and Language · Computer Science 2021-10-08 Orevaoghene Ahia , Julia Kreutzer , Sara Hooker

In this work, we present a variety of novel information-theoretic generalization bounds for learning algorithms, from the supersample setting of Steinke & Zakynthinou (2020)-the setting of the "conditional mutual information" framework. Our…

Machine Learning · Statistics 2023-06-16 Ziqiao Wang , Yongyi Mao

Traditional supervised learning aims to train a classifier in the closed-set world, where training and test samples share the same label space. In this paper, we target a more challenging and realistic setting: open-set learning (OSL),…

Machine Learning · Computer Science 2021-07-01 Zhen Fang , Jie Lu , Anjin Liu , Feng Liu , Guangquan Zhang

Explainability of neural network prediction is essential to understand feature importance and gain interpretable insight into neural network performance. However, explanations of neural network outcomes are mostly limited to visualization,…

Machine Learning · Computer Science 2023-07-13 Arnab Neelim Mazumder , Niall Lyons , Ashutosh Pandey , Avik Santra , Tinoosh Mohsenin

In sentence compression, the task of shortening sentences while retaining the original meaning, models tend to be trained on large corpora containing pairs of verbose and compressed sentences. To remove the need for paired corpora, we…

Computation and Language · Computer Science 2018-09-11 Thibault Févry , Jason Phang

We study a simple learning algorithm for binary classification. Instead of predicting with the best hypothesis in the hypothesis class, that is, the hypothesis that minimizes the training error, our algorithm predicts with a weighted…

Statistics Theory · Mathematics 2007-06-13 Yoav Freund , Yishay Mansour , Robert E. Schapire

The ability of likelihood-based probabilistic models to generalize to unseen data is central to many machine learning applications such as lossless compression. In this work, we study the generalization of a popular class of probabilistic…

Machine Learning · Statistics 2022-10-18 Mingtian Zhang , Peter Hayes , David Barber

Pruning and quantization techniques have been broadly successful in reducing the number of parameters needed for large neural networks, yet theoretical justification for their empirical success falls short. We consider a randomized greedy…

Machine Learning · Computer Science 2025-12-09 Houssam El Cheairi , David Gamarnik , Rahul Mazumder

Large language model (LLM) tokenizers act as structured compressors: by mapping text to discrete token sequences, they determine token count (and thus compute and context usage) and the statistical structure seen by downstream models.…

Information Theory · Computer Science 2026-01-15 Mete Erdogan , Abhiram Gorle , Shubham Chandak , Mert Pilanci , Tsachy Weissman

Linear models are used in online decision making, such as in machine learning, policy algorithms, and experimentation platforms. Many engineering systems that use linear models achieve computational efficiency through distributed systems…

Machine Learning · Computer Science 2021-03-04 Jeffrey Wong , Eskil Forsell , Randall Lewis , Tobias Mao , Matthew Wardrop

Understanding generalization is crucial to confidently engineer and deploy machine learning models, especially when deployment implies a shift in the data domain. For such domain adaptation problems, we seek generalization bounds which are…

Machine Learning · Computer Science 2023-03-16 Adam Breitholtz , Fredrik D. Johansson

We present an extensive analysis of relative deviation bounds, including detailed proofs of two-sided inequalities and their implications. We also give detailed proofs of two-sided generalization bounds that hold in the general case of…

Machine Learning · Computer Science 2016-04-06 Corinna Cortes , Spencer Greenberg , Mehryar Mohri

In transfer learning, the learner leverages auxiliary data to improve generalization on a main task. However, the precise theoretical understanding of when and how auxiliary data help remains incomplete. We provide new insights on this…

Machine Learning · Computer Science 2026-03-31 Meitong Liu , Christopher Jung , Rui Li , Xue Feng , Han Zhao

We examine the coordinated and universal rate-efficient sampling of a subset of correlated discrete memoryless sources followed by lossy compression of the sampled sources. The goal is to reconstruct a predesignated subset of sources within…

Information Theory · Computer Science 2017-06-23 Vinay Praneeth Boda , Prakash Narayan

Energy-based probabilistic models learned by maximizing the likelihood of the data are limited by the intractability of the partition function. A widely used workaround is to maximize the pseudo-likelihood, which replaces the global…

Statistical Mechanics · Physics 2026-03-31 Francesco D'Amico , Dario Bocchi , Luca Maria Del Bono , Saverio Rossi , Matteo Negri

Deep learning models learn to fit training data while they are highly expected to generalize well to testing data. Most works aim at finding such models by creatively designing architectures and fine-tuning parameters. To adapt to…

Computer Vision and Pattern Recognition · Computer Science 2018-09-10 Tianyang Wang , Jun Huan , Bo Li

Large Language Models (LLMs) have transformed natural language processing tasks successfully. Yet, their large size and high computational needs pose challenges for practical use, especially in resource-limited settings. Model compression…

Computation and Language · Computer Science 2024-07-31 Xunyu Zhu , Jian Li , Yong Liu , Can Ma , Weiping Wang

Most reinforcement learning algorithms take advantage of an experience replay buffer to repeatedly train on samples the agent has observed in the past. Not all samples carry the same amount of significance and simply assigning equal…

Machine Learning · Computer Science 2023-11-02 Shivakanth Sujit , Somjit Nath , Pedro H. M. Braga , Samira Ebrahimi Kahou

Adaptive sampling theory has shown that, with proper assumptions on the signal class, algorithms exist to reconstruct a signal in $\mathbb{R}^{d}$ with an optimal number of samples. We generalize this problem to the case of spatial signals,…

Machine Learning · Statistics 2017-02-20 John Lipor , Brandon Wong , Donald Scavia , Branko Kerkez , Laura Balzano