English
Related papers

Related papers: A Recovery Guarantee for Sparse Neural Networks

200 papers

Previous work has demonstrated that MLPs within ReLU Transformers exhibit high levels of sparsity, with many of their activations equal to zero for any given token. We build on that work to more deeply explore how token-level sparsity…

Machine Learning · Computer Science 2024-07-11 Cody Wild , Jesper Anderson

Decision trees are widely used for their low computational cost, good predictive performance, and ability to assess the importance of features. Though often used in practice for feature selection, the theoretical guarantees of these methods…

Machine Learning · Statistics 2023-03-09 Kiarash Banihashem , MohammadTaghi Hajiaghayi , Max Springer

Overparameterized neural networks can interpolate a given dataset in many different ways, prompting the fundamental question: which among these solutions should we prefer, and what explicit regularization strategies will provably yield…

Machine Learning · Statistics 2026-01-28 Julia Nakhleh , Robert D. Nowak

The Strong Lottery Ticket Hypothesis (SLTH) posits that large, randomly initialized neural networks contain sparse subnetworks capable of approximating a target function at initialization without training, suggesting that pruning alone is…

Machine Learning · Computer Science 2026-03-05 Davide Ferre' , Frédéric Giroire , Frederik Mallmann-Trenn , Emanuele Natale

We study the problem of jointly sparse support recovery with 1-bit compressive measurements in a sensor network. Sensors are assumed to observe sparse signals having the same but unknown sparse support. Each sensor quantizes its measurement…

Information Theory · Computer Science 2015-06-02 Vipul Gupta , Bhavya Kailkhura , Thakshila Wimalajeewa , Pramod K. Varshney

In this paper, we introduce a weighted $\ell_2/\ell_1$ minimization to recover block sparse signals with arbitrary prior support information. When partial prior support information is available, a sufficient condition based on the high…

Information Theory · Computer Science 2017-06-30 Wengu Chen , Huanmin Ge

This paper introduces recovery thresholding hyperinterpolations, a novel class of methods for sparse signal reconstruction in the presence of noise. We develop a framework that integrates thresholding operators--including hard thresholding,…

Numerical Analysis · Mathematics 2025-07-25 Congpei An , Jiashu Ran

We consider a structured estimation problem where an observed matrix is assumed to be generated as an $s$-sparse linear combination of $N$ given $n\times n$ positive-semidefinite matrices. Recovering the unknown $N$-dimensional and…

Information Theory · Computer Science 2020-03-27 Fabian Jaensch , Peter Jung

Intensively growing approach in signal processing and acquisition, the Compressive Sensing approach, allows sparse signals to be recovered from small number of randomly acquired signal coefficients. This paper analyses some of the commonly…

Signal Processing · Electrical Eng. & Systems 2018-02-21 Tamara Koljensic , Caslav Labudovic

Overwhelming theoretical and empirical evidence shows that mildly overparametrized neural networks -- those with more connections than the size of the training data -- are often able to memorize the training data with $100\%$ accuracy. This…

Machine Learning · Computer Science 2020-06-04 Roman Vershynin

We present a novel stagewise strategy for improving greedy algorithms for sparse recovery. We demonstrate its efficiency both for synthesis and analysis sparse priors, where in both cases we demonstrate its computational efficiency and…

Numerical Analysis · Mathematics 2020-12-02 Guy Leibovitz , Raja Giryes

Neural networks can be trained to solve regression problems by using gradient-based methods to minimize the square loss. However, practitioners often prefer to reformulate regression as a classification problem, observing that training on…

Machine Learning · Computer Science 2023-03-02 Lawrence Stewart , Francis Bach , Quentin Berthet , Jean-Philippe Vert

Deep neural networks have emerged as powerful tools for learning operators defined over infinite-dimensional function spaces. However, existing theories frequently encounter difficulties related to dimensionality and limited…

Machine Learning · Computer Science 2026-05-12 Jianfei Li , Shuo Huang , Han Feng , Ding-Xuan Zhou , Gitta Kutyniok

Deep neural networks tend to underestimate uncertainty and produce overly confident predictions. Recently proposed solutions, such as MC Dropout and SDENet, require complex training and/or auxiliary out-of-distribution data. We propose a…

Machine Learning · Computer Science 2021-10-14 Akib Mashrur , Wei Luo , Nayyar A. Zaidi , Antonio Robles-Kelly

The observation that activation sparsity emerges in MLP blocks of standardly trained Transformers offers an opportunity to drastically reduce computation costs without sacrificing performance. To theoretically explain this phenomenon,…

Machine Learning · Computer Science 2026-05-26 Ze Peng , Jian Zhang , Lei Qi , Yang Gao , Yinghuan Shi

We consider the problem of sparse signal recovery from noisy measurements. Many of frequently used recovery methods rely on some sort of tuning depending on either noise or signal parameters. If no estimates for either of them are…

Information Theory · Computer Science 2020-10-20 Hendrik Bernd Petersen , Peter Jung

The possibility for one to recover the parameters-weights and biases-of a neural network thanks to the knowledge of its function on a subset of the input space can be, depending on the situation, a curse or a blessing. On one hand,…

Statistics Theory · Mathematics 2023-05-15 Joachim Bona-Pellissier , François Bachoc , François Malgouyres

In this paper, we consider the sparse phase retrieval problem, recovering an $s$-sparse signal $\bm{x}^{\natural}\in\mathbb{R}^n$ from $m$ phaseless samples $y_i=|\langle\bm{x}^{\natural},\bm{a}_i\rangle|$ for $i=1,\ldots,m$. Existing…

Numerical Analysis · Mathematics 2021-10-15 Jian-Feng Cai , Jingzhi Li , Xiliang Lu , Juntao You

Plasticity Loss is an increasingly important phenomenon that refers to the empirical observation that as a neural network is continually trained on a sequence of changing tasks, its ability to adapt to a new task diminishes over time. We…

Machine Learning · Computer Science 2025-09-30 Vivek F. Farias , Adam D. Jozefiak

Recent advances in artificial intelligence have relied heavily on increasingly large neural networks, raising concerns about their computational and environmental costs. This paper investigates whether simpler, sparser networks can maintain…

Machine Learning · Computer Science 2025-11-04 C. Díaz-Faloh , R. Mulet