English
Related papers

Related papers: Statistical limits of dictionary learning: random …

200 papers

The choice of the parameter value for regularized inverse problems is critical to the results and remains a topic of interest. This article explores a criterion for selecting a good parameter value by maximizing the probability of the data,…

Numerical Analysis · Mathematics 2020-02-11 Toby Sanders , Rodrigo B. Platte , Robert D. Skeel

Understanding the learning dynamics of neural networks is one of the key issues for the improvement of optimization algorithms as well as for the theoretical comprehension of why deep neural nets work so well today. In this paper, we…

Machine Learning · Statistics 2021-03-18 Zhenyu Liao , Romain Couillet

Most existing algorithms for dictionary learning assume that all entries of the (high-dimensional) input data are fully observed. However, in several practical applications (such as hyper-spectral imaging or blood glucose monitoring), only…

Machine Learning · Statistics 2018-04-26 Thanh V. Nguyen , Akshay Soni , Chinmay Hegde

In this paper, we present a local information theoretic approach to explicitly learn probabilistic clustering of a discrete random variable. Our formulation yields a convex maximization problem for which it is NP-hard to find the global…

Machine Learning · Computer Science 2018-10-12 David Qiu , Anuran Makur , Lizhong Zheng

Sparse coding or sparse dictionary learning has been widely used to recover underlying structure in many kinds of natural data. Here, we provide conditions guaranteeing when this recovery is universal; that is, when sparse codes and…

Neurons and Cognition · Quantitative Biology 2016-11-18 Christopher J. Hillar , Friedrich T. Sommer

Dense passage retrieval (DPR) is the first step in the retrieval augmented generation (RAG) paradigm for improving the performance of large language models (LLM). DPR fine-tunes pre-trained networks to enhance the alignment of the…

Computation and Language · Computer Science 2024-10-07 Benjamin Reichman , Larry Heck

For better learning, large datasets are often split into small batches and fed sequentially to the predictive model. In this paper, we study such batch decompositions from a probabilistic perspective. We assume that data points (possibly…

Machine Learning · Computer Science 2025-04-10 Ghurumuruhan Ganesan

There exist many high-dimensional data in real-world applications such as biology, computer vision, and social networks. Feature selection approaches are devised to confront with high-dimensional data challenges with the aim of efficient…

Machine Learning · Computer Science 2021-06-22 Mohsen Ghassemi Parsa , Hadi Zare , Mehdi Ghatee

We study the problem of approximating an unknown function $f:\mathbb{R}\to\mathbb{R}$ by a degree-$d$ polynomial using as few function evaluations as possible, where error is measured with respect to a probability distribution $\mu$.…

Data Structures and Algorithms · Computer Science 2025-08-11 Chris Camaño , Raphael A. Meyer , Kevin Shu

Factorizing low-rank matrices has many applications in machine learning and statistics. For probabilistic models in the Bayes optimal setting, a general expression for the mutual information has been proposed using heuristic statistical…

Information Theory · Computer Science 2017-03-24 Jean Barbier , Mohamad Dia , Nicolas Macris , Florent Krzakala , Thibault Lesieur , Lenka Zdeborova

Smoothed analysis is a powerful paradigm in overcoming worst-case intractability in unsupervised learning and high-dimensional data analysis. While polynomial time smoothed analysis guarantees have been obtained for worst-case intractable…

Data Structures and Algorithms · Computer Science 2019-04-25 Aditya Bhaskara , Aidao Chen , Aidan Perreault , Aravindan Vijayaraghavan

As scaling laws push the training of frontier large language models (LLMs) toward ever-growing data requirements, training pipelines are approaching a regime where much of the publicly available online text may be consumed. At the same…

Machine Learning · Computer Science 2026-03-13 Giorgio Racca , Michal Valko , Amartya Sanyal

Modern technologies are producing a wealth of data with complex structures. For instance, in two-dimensional digital imaging, flow cytometry, and electroencephalography, matrix type covariates frequently arise when measurements are obtained…

Methodology · Statistics 2013-10-22 Hua Zhou , Lexin Li

Sparse representations with learned dictionaries have been successful in several image analysis applications. In this paper, we propose and analyze the framework of ensemble sparse models, and demonstrate their utility in image restoration…

Computer Vision and Pattern Recognition · Computer Science 2013-02-28 Karthikeyan Natesan Ramamurthy , Jayaraman J. Thiagarajan , Prasanna Sattigeri , Andreas Spanias

We aim at the solution of inverse problems in imaging, by combining a penalized sparse representation of image patches with an unconstrained smooth one. This allows for a straightforward interpretation of the reconstruction. We formulate…

Image and Video Processing · Electrical Eng. & Systems 2025-03-18 Stanislas Ducotterd , Sebastian Neumayer , Michael Unser

Autoregressive language models (ARMs) have been shown to memorize and occasionally reproduce training data verbatim, raising concerns about privacy and copyright liability. Diffusion language models (DLMs) have recently emerged as a…

Computation and Language · Computer Science 2026-03-04 Xiaoyu Luo , Wenrui Yu , Qiongxiu Li , Johannes Bjerva

Latent variable models with hidden binary units appear in various applications. Learning such models, in particular in the presence of noise, is a challenging computational problem. In this paper we propose a novel spectral approach to this…

Machine Learning · Statistics 2018-02-28 Ariel Jaffe , Roi Weiss , Shai Carmi , Yuval Kluger , Boaz Nadler

Text generation tasks, including translation, summarization, language models, and etc. see rapid growth during recent years. Despite the remarkable achievements, the repetition problem has been observed in nearly all text generation models…

Computation and Language · Computer Science 2021-03-23 Zihao Fu , Wai Lam , Anthony Man-Cho So , Bei Shi

Sparse matrix factorization is a popular tool to obtain interpretable data decompositions, which are also effective to perform data completion or denoising. Its applicability to large datasets has been addressed with online and randomized…

Machine Learning · Statistics 2017-11-15 Arthur Mensch , Julien Mairal , Bertrand Thirion , Gaël Varoquaux

In an era of unprecedented deluge of (mostly unstructured) data, graphs are proving more and more useful, across the sciences, as a flexible abstraction to capture complex relationships between complex objects. One of the main challenges…

Disordered Systems and Neural Networks · Physics 2016-10-17 Alaa Saade
‹ Prev 1 8 9 10 Next ›