English
Related papers

Related papers: Gradient-Based Feature Learning under Structured D…

200 papers

The success of deep neural networks largely depends on the statistical structure of the training data. While learning dynamics and generalization on isotropic data are well-established, the impact of pronounced anisotropy on these crucial…

Machine Learning · Statistics 2026-01-13 Taishi Watanabe , Ryo Karakida , Jun-nosuke Teramae

This paper investigates low-rank structure in the gradients of the training loss for two-layer neural networks while relaxing the usual isotropy assumptions on the training data and parameters. We consider a spiked data model in which the…

Machine Learning · Computer Science 2025-10-03 Rishi Sonthalia , Michael Murray , Guido Montúfar

We investigate the problem of learning a Single Index Model (SIM)- a popular model for studying the ability of neural networks to learn features - from anisotropic Gaussian inputs by training a neuron using vanilla Stochastic Gradient…

Machine Learning · Statistics 2025-04-01 Guillaume Braun , Minh Ha Quang , Masaaki Imaizumi

Feature learning is widely regarded as the key mechanism distinguishing neural networks from fixed-kernel methods, yet its impact on the induced function space remains poorly understood. In this work, we precisely characterize how the…

Machine Learning · Statistics 2026-05-19 João Lobo , Bruno Loureiro , Long Tran-Than , Fanghui Liu

In artificial neural networks trained with gradient descent, the weights used for processing stimuli are also used during backward passes to calculate gradients. For the real brain to approximate gradients, gradient information would have…

Neurons and Cognition · Quantitative Biology 2020-02-04 Jordan Guerguiev , Konrad P. Kording , Blake A. Richards

The success of deep learning in high-dimensional settings is often attributed to the presence of low-dimensional structure in real-world data. While standard theoretical models typically assume that this structure lies in the target…

Machine Learning · Computer Science 2026-05-15 Elisabetta Cornacchia , Laurent Massoulié

Random matrix theory has proven to be a valuable tool in analyzing the generalization of linear models. However, the generalization properties of even two-layer neural networks trained by gradient descent remain poorly understood. To…

Statistics Theory · Mathematics 2024-10-21 Jiping Li , Rishi Sonthalia

Gradient descent prevails in artificial neural network training, but seems inept for spiking neural networks as small parameter changes can cause sudden, disruptive (dis-)appearances of spikes. Here, we demonstrate exact gradient descent…

Neurons and Cognition · Quantitative Biology 2025-01-29 Christian Klos , Raoul-Martin Memmesheimer

The problem of learning single index and multi index models has gained significant interest as a fundamental task in high-dimensional statistics. Many recent works have analysed gradient-based methods, particularly in the setting of…

Machine Learning · Computer Science 2025-07-22 Elisabetta Cornacchia , Dan Mikulincer , Elchanan Mossel

Brain-inspired learning models attempt to mimic the cortical architecture and computations performed in the neurons and synapses constituting the human brain to achieve its efficiency in cognitive tasks. In this work, we present…

Neural and Evolutionary Computing · Computer Science 2017-03-21 Priyadarshini Panda , Gopalakrishnan Srinivasan , Kaushik Roy

In this manuscript, we investigate the problem of how two-layer neural networks learn features from data, and improve over the kernel regime, after being trained with a single gradient descent step. Leveraging the insight from (Ba et al.,…

Machine Learning · Statistics 2024-09-06 Hugo Cui , Luca Pesce , Yatin Dandi , Florent Krzakala , Yue M. Lu , Lenka Zdeborová , Bruno Loureiro

We present a method of estimating the gradient of an objective function with respect to the synaptic weights of a spiking neural network. The method works by measuring the fluctuations in the objective function in response to dynamic…

Neurons and Cognition · Quantitative Biology 2007-05-23 Ila R. Fiete , H. Sebastian Seung

Feature learning is thought to be one of the fundamental reasons for the success of deep neural networks. It is rigorously known that in two-layer fully-connected neural networks under certain conditions, one step of gradient descent on the…

Machine Learning · Statistics 2025-04-11 Behrad Moniri , Donghwan Lee , Hamed Hassani , Edgar Dobriban

Causal structure learning has been a challenging task in the past decades and several mainstream approaches such as constraint- and score-based methods have been studied with theoretical guarantees. Recently, a new approach has transformed…

Machine Learning · Computer Science 2019-11-19 Ignavier Ng , Shengyu Zhu , Zhitang Chen , Zhuangyan Fang

Few neural architectures lend themselves to provable learning with gradient based methods. One popular model is the single-index model, in which labels are produced by composing an unknown linear projection with a possibly unknown scalar…

Machine Learning · Computer Science 2023-10-04 Aaron Zweig , Joan Bruna

To understand feature learning dynamics in neural networks, recent theoretical works have focused on gradient-based learning of Gaussian single-index models, where the label is a nonlinear function of a latent one-dimensional projection of…

Machine Learning · Computer Science 2025-10-27 Konstantinos Christopher Tsiolis , Alireza Mousavi-Hosseini , Murat A. Erdogdu

Spiking neural networks play an important role in brain-like neuromorphic computations and in studying working mechanisms of neural circuits. One drawback of training a large scale spiking neural network is that updating all weights is…

Neurons and Cognition · Quantitative Biology 2024-08-15 Zhanghan Lin , Haiping Huang

Event-based neuromorphic systems promise to reduce the energy consumption of deep learning tasks by replacing expensive floating point operations on dense matrices by low power sparse and asynchronous operations on spike events. While these…

Neural and Evolutionary Computing · Computer Science 2019-06-04 Johannes Christian Thiele , Olivier Bichler , Antoine Dupret

Often in language and other areas of cognition, whether two components of an object are identical or not determines if it is well formed. We call such constraints identity effects. When developing a system to learn well-formedness from…

Machine Learning · Computer Science 2022-03-03 S. Brugiapaglia , M. Liu , P. Tupper

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
‹ Prev 1 2 3 10 Next ›