English
Related papers

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

200 papers

Energy-based learning is a powerful framework for generative modelling, but its training is inherently non-convex, leading potentially to sensitivity to initialisation, poor local optima, and unstable gradient dynamics. We present a…

Machine Learning · Computer Science 2026-05-11 Aurélien Decelle , Alfonso de Jesús Navas Gómez , Beatriz Seoane

We study the recovery of multiple high-dimensional signals from two noisy, correlated modalities: a spiked matrix and a spiked tensor sharing a common low-rank structure. This setting generalizes classical spiked matrix and tensor models,…

Machine Learning · Statistics 2025-06-04 Hugo Tabanelli , Pierre Mergny , Lenka Zdeborova , Florent Krzakala

Deep classifiers are known to rely on spurious features $\unicode{x2013}$ patterns which are correlated with the target on the training data but not inherently relevant to the learning problem, such as the image backgrounds when classifying…

Machine Learning · Computer Science 2022-10-21 Pavel Izmailov , Polina Kirichenko , Nate Gruver , Andrew Gordon Wilson

A significant obstacle in the development of robust machine learning models is covariate shift, a form of distribution shift that occurs when the input distributions of the training and test sets differ while the conditional label…

Machine Learning · Statistics 2021-11-17 Nilesh Tripuraneni , Ben Adlam , Jeffrey Pennington

We study the relationship between gradient-based optimization of parametric models (e.g., neural networks) and optimization of linear combinations of random features. Our main result shows that if a parametric model can be learned using…

Machine Learning · Computer Science 2025-05-16 Ari Karchmer , Eran Malach

Grokking typically achieves similar loss to ordinary, "steady", learning. We ask whether these different learning paths - grokking versus ordinary training - lead to fundamental differences in the learned models. To do so we compare the…

The spiking neural network (SNN), as a promising brain-inspired computational model with binary spike information transmission mechanism, rich spatially-temporal dynamics, and event-driven characteristics, has received extensive attention.…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Yufei Guo , Xuhui Huang , Zhe Ma

Stochastic gradient descent (SGD) and adaptive gradient methods, such as Adam and RMSProp, have been widely used in training deep neural networks. We empirically show that while the difference between the standard generalization performance…

Machine Learning · Computer Science 2023-11-30 Avery Ma , Yangchen Pan , Amir-massoud Farahmand

Machine learning models trained with \emph{stochastic} gradient descent (SGD) can generalize better than those trained with deterministic gradient descent (GD). In this work, we study SGD's impact on generalization through the lens of the…

Machine Learning · Computer Science 2025-12-09 Hongjian Lan , Yucong Liu , Florian Schäfer

Physics-informed neural networks and operator networks have shown promise for effectively solving equations modeling physical systems. However, these networks can be difficult or impossible to train accurately for some systems of equations.…

Machine Learning · Computer Science 2023-11-22 Amanda A Howard , Sarah H Murphy , Shady E Ahmed , Panos Stinis

Spiking Neural Networks (SNNs) are being explored for their potential energy efficiency resulting from sparse, event-driven computations. Many recent works have demonstrated effective backpropagation for deep Spiking Neural Networks (SNNs)…

Neural and Evolutionary Computing · Computer Science 2020-03-04 Jason M. Allred , Steven J. Spencer , Gopalakrishnan Srinivasan , Kaushik Roy

This paper presents a constructive algorithm that achieves successful one-shot learning of hidden spike-patterns in a competitive detection task. It has previously been shown (Masquelier et al., 2008) that spike-timing-dependent plasticity…

Neurons and Cognition · Quantitative Biology 2017-08-31 Toby Lightheart , Steven Grainger , Tien-Fu Lu

Despite recent advances, goal-directed generation of structured discrete data remains challenging. For problems such as program synthesis (generating source code) and materials design (generating molecules), finding examples which satisfy…

Machine Learning · Computer Science 2020-10-26 Amina Mollaysa , Brooks Paige , Alexandros Kalousis

Teacher-student models provide a framework in which the typical-case performance of high-dimensional supervised learning can be described in closed form. The assumptions of Gaussian i.i.d. input data underlying the canonical teacher-student…

Spiking neural networks (SNNs) promise orders-of-magnitude efficiency gains by communicating with sparse, event-driven spikes rather than dense numerical activations. However, most training pipelines either rely on surrogate-gradient…

Neural and Evolutionary Computing · Computer Science 2025-12-17 Arman Ferdowsi , Atakan Aral

We consider structure discovery of undirected graphical models from observational data. Inferring likely structures from few examples is a complex task often requiring the formulation of priors and sophisticated inference procedures.…

Machine Learning · Statistics 2017-08-04 Eugene Belilovsky , Kyle Kastner , Gaël Varoquaux , Matthew Blaschko

Previous studies have shown that spike-timing-dependent plasticity (STDP) can be used in spiking neural networks (SNN) to extract visual features of low or intermediate complexity in an unsupervised manner. These studies, however, used…

Computer Vision and Pattern Recognition · Computer Science 2018-03-12 Saeed Reza Kheradpisheh , Mohammad Ganjtabesh , Simon J Thorpe , Timothée Masquelier

We study the first gradient descent step on the first-layer parameters $\boldsymbol{W}$ in a two-layer neural network: $f(\boldsymbol{x}) = \frac{1}{\sqrt{N}}\boldsymbol{a}^\top\sigma(\boldsymbol{W}^\top\boldsymbol{x})$, where…

Machine Learning · Statistics 2022-05-04 Jimmy Ba , Murat A. Erdogdu , Taiji Suzuki , Zhichao Wang , Denny Wu , Greg Yang

Although statistical learning theory provides a robust framework to understand supervised learning, many theoretical aspects of deep learning remain unclear, in particular how different architectures may lead to inductive bias when trained…

Machine Learning · Computer Science 2024-03-27 Cédric Gerbelot , Avetik Karagulyan , Stefani Karp , Kavya Ravichandran , Menachem Stern , Nathan Srebro

The adaptive changes in synaptic efficacy that occur between spiking neurons have been demonstrated to play a critical role in learning for biological neural networks. Despite this source of inspiration, many learning focused applications…

Neural and Evolutionary Computing · Computer Science 2022-05-30 Samuel Schmidgall , Julia Ashkanazy , Wallace Lawson , Joe Hays