English
Related papers

Related papers: Bayes-optimal learning of an extensive-width neura…

200 papers

We consider the problem of learning a target function corresponding to a deep, extensive-width, non-linear neural network with random Gaussian weights. We consider the asymptotic limit where the number of samples, the input dimension and…

Machine Learning · Statistics 2023-09-07 Hugo Cui , Florent Krzakala , Lenka Zdeborová

Although deep learning has shown its powerful performance in many applications, the mathematical principles behind neural networks are still mysterious. In this paper, we consider the problem of learning a one-hidden-layer neural network…

Machine Learning · Computer Science 2019-07-17 Shuhao Xia , Yuanming Shi

In the matrix sensing problem, one wishes to reconstruct a matrix from (possibly noisy) observations of its linear projections along given directions. We consider this model in the high-dimensional limit: while previous works on this model…

Machine Learning · Statistics 2025-11-13 Yizhou Xu , Antoine Maillard , Lenka Zdeborová , Florent Krzakala

The sparse Beyesian learning (also referred to as Bayesian compressed sensing) algorithm is one of the most popular approaches for sparse signal recovery, and has demonstrated superior performance in a series of experiments. Nevertheless,…

Information Theory · Computer Science 2015-01-21 Fuwei Li , Jun Fang , Huiping Duan , Zhi Chen , Hongbin Li

Supervised learning problems with side information in the form of a network arise frequently in applications in genomics, proteomics and neuroscience. For example, in genetic applications, the network side information can accurately capture…

Statistics Theory · Mathematics 2024-10-24 Sagnik Nandy , Subhabrata Sen

In this paper we study the problem of learning a shallow artificial neural network that best fits a training data set. We study this problem in the over-parameterized regime where the number of observations are fewer than the number of…

Machine Learning · Computer Science 2022-08-25 Mahdi Soltanolkotabi , Adel Javanmard , Jason D. Lee

For a large class of feature maps we provide a tight asymptotic characterisation of the test error associated with learning the readout layer, in the high-dimensional limit where the input dimension, hidden layer widths, and number of…

Machine Learning · Statistics 2024-06-11 Dominik Schröder , Daniil Dmitriev , Hugo Cui , Bruno Loureiro

We consider the task of estimating a low-rank matrix from non-linear and noisy observations. We prove a strong universality result showing that Bayes-optimal performances are characterized by an equivalent Gaussian model with an effective…

Machine Learning · Statistics 2024-03-08 Pierre Mergny , Justin Ko , Florent Krzakala , Lenka Zdeborová

We propose a novel active learning strategy for regression, which is model-agnostic, robust against model mismatch, and interpretable. Assuming that a small number of initial samples are available, we derive the optimal training density…

Machine Learning · Computer Science 2021-07-27 Danny Panknin , Klaus Robert Müller , Shinichi Nakajima

We study the high-dimensional asymptotics of empirical risk minimization (ERM) in over-parametrized two-layer neural networks with quadratic activations trained on synthetic data. We derive sharp asymptotics for both training and test…

Machine Learning · Statistics 2026-02-03 Vittorio Erba , Emanuele Troiani , Lenka Zdeborová , Florent Krzakala

We study the dynamics of optimization and the generalization properties of one-hidden layer neural networks with quadratic activation function in the over-parametrized regime where the layer width $m$ is larger than the input dimension $d$.…

Machine Learning · Computer Science 2021-03-22 Stefano Sarao Mannelli , Eric Vanden-Eijnden , Lenka Zdeborová

Much of Bayesian inference centers around the design of estimators for inverse problems which are optimal assuming the data comes from a known prior. But what do these optimality guarantees mean if the prior is unknown? In recent years,…

Machine Learning · Computer Science 2024-09-20 Aayush Karan , Kulin Shah , Sitan Chen , Yonina C. Eldar

We provide new theoretical insights on why over-parametrization is effective in learning neural networks. For a $k$ hidden node shallow network with quadratic activation and $n$ training data points, we show as long as $ k \ge \sqrt{2n}$,…

Machine Learning · Computer Science 2018-06-18 Simon S. Du , Jason D. Lee

Nonlinear function estimation is core to modern machine learning applications. In this paper, to perform nonlinear function estimation, we reduce a nonlinear inverse problem to a linear one using a polynomial kernel expansion. These kernels…

Information Theory · Computer Science 2019-10-02 Hangjin Liu , You , Zhou , Ahmad Beirami , Dror Baron

We introduce the attention-indexed model (AIM), a theoretical framework for analyzing learning in deep attention layers. Inspired by multi-index models, AIM captures how token-level outputs emerge from layered bilinear interactions over…

Machine Learning · Computer Science 2026-02-03 Fabrizio Boncoraglio , Emanuele Troiani , Vittorio Erba , Lenka Zdeborová

We consider the approximation of functions by 2-layer neural networks with a small number of hidden weights based on the squared loss and small datasets. Due to the highly non-convex energy landscape, gradient-based training often suffers…

Machine Learning · Computer Science 2025-08-14 Johannes Hertrich , Sebastian Neumayer

We study the problem of learning an unknown function using random feature models. Our main contribution is an exact asymptotic analysis of such learning problems with Gaussian data. Under mild regularity conditions for the feature matrix,…

Information Theory · Computer Science 2020-08-28 Oussama Dhifallah , Yue M. Lu

One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can achieve zero training loss even though the objective function is non-convex and non-smooth. This paper demystifies…

Machine Learning · Computer Science 2019-02-06 Simon S. Du , Xiyu Zhai , Barnabas Poczos , Aarti Singh

We provide exact asymptotic expressions for the performance of regression by an $L-$layer deep random feature (RF) model, where the input is mapped through multiple random embedding and non-linear activation functions. For this purpose, we…

Machine Learning · Statistics 2023-02-14 David Bosch , Ashkan Panahi , Babak Hassibi

In the literature on deep neural networks, there is considerable interest in developing activation functions that can enhance neural network performance. In recent years, there has been renewed scientific interest in proposing activation…

Machine Learning · Computer Science 2023-04-20 Mohamed Fakhfakh , Lotfi Chaari
‹ Prev 1 2 3 10 Next ›