English
Related papers

Related papers: Understanding Gradient Descent through the Trainin…

200 papers

We conjecture that the inherent difference in generalisation between adaptive and non-adaptive gradient methods in deep learning stems from the increased estimation noise in the flattest directions of the true loss surface. We demonstrate…

Machine Learning · Statistics 2022-03-17 Diego Granziol , Nicholas Baskerville

This paper presents a locally decoupled network parameter learning with local propagation. Three elements are taken into account: (i) sets of nonlinear transforms that describe the representations at all nodes, (ii) a local objective at…

Machine Learning · Computer Science 2018-05-22 Dimche Kostadinov , Behrooz Razeghi , Sohrab Ferdowsi , Slava Voloshynovskiy

The aim of this paper is to develop a general framework for training neural networks (NNs) in a distributed environment, where training data is partitioned over a set of agents that communicate with each other through a sparse, possibly…

Machine Learning · Statistics 2017-04-21 Simone Scardapane , Paolo Di Lorenzo

Deep neural networks are prone to learning shortcuts, spurious correlations present in the training data that undermine out-of-distribution (OOD) generalization. Most prior work mitigates shortcut learning through input-space reweighting,…

Machine Learning · Computer Science 2026-03-10 Shivam Pal , Sakshi Varshney , Piyush Rai

Neural networks are commonly trained to make predictions through learning algorithms. Contrastive Hebbian learning, which is a powerful rule inspired by gradient backpropagation, is based on Hebb's rule and the contrastive divergence…

Machine Learning · Computer Science 2018-06-21 Georgios Detorakis , Travis Bartley , Emre Neftci

We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervised and…

Machine Learning · Computer Science 2022-10-17 Lang Huang , Chao Zhang , Hongyang Zhang

The phenomenon of distinct behaviors exhibited by neural networks under varying scales of initialization remains an enigma in deep learning research. In this paper, based on the earlier work by Luo et al.~\cite{luo2021phase}, we present a…

Machine Learning · Computer Science 2026-04-02 Zhengan Chen , Yuqing Li , Tao Luo , Zhangchen Zhou , Zhi-Qin John Xu

In this work, we propose a notion of practical learnability grounded in finite sample settings, and develop a conjugate learning theoretical framework based on convex conjugate duality to characterize this learnability property. Building on…

Machine Learning · Statistics 2026-02-20 Binchuan Qi

In a series of recent theoretical works, it was shown that strongly over-parameterized neural networks trained with gradient-based methods could converge exponentially fast to zero training loss, with their parameters hardly varying. In…

Optimization and Control · Mathematics 2020-01-08 Lenaic Chizat , Edouard Oyallon , Francis Bach

Hebbian learning is a key principle underlying learning in biological neural networks. We relate a Hebbian spike-timing-dependent plasticity rule to noisy gradient descent with respect to a non-convex loss function on the probability…

Machine Learning · Computer Science 2026-01-14 Niklas Dexheimer , Sascha Gaudlitz , Johannes Schmidt-Hieber

This paper develops the angular and static-channel component of Geometric and Spectral Alignment for residual Jacobian chains. Starting from Cartan-coordinate rigidity and fitted effective-rank windows, we study how dominant singular…

Machine Learning · Computer Science 2026-05-05 Ziran Liu , Wei Wang , Jinhao Wang , Pengcheng Wang , Xinyi Sui , Cihan Ruan , Nam Ling , Wei Jiang

The study of Neural Tangent Kernels (NTKs) has provided much needed insight into convergence and generalization properties of neural networks in the over-parametrized (wide) limit by approximating the network using a first-order Taylor…

Machine Learning · Statistics 2023-02-02 Alistair Shilton , Sunil Gupta , Santu Rana , Svetha Venkatesh

The discrete spectrum of complex Jacobi matrices that are compact perturbations of the discrete laplacian is under consideration. The rate of stabilization for the the matrix entries which provides finiteness of the discrete spectrum and is…

Spectral Theory · Mathematics 2007-05-23 I. Egorova , L. Golinskii

Deep learning involves navigating a high-dimensional loss landscape over the neural network parameter space. Over the course of training, complex computational structures form and re-form inside the neural network, leading to shifts in…

Machine Learning · Computer Science 2025-08-04 Jesse Hoogland , George Wang , Matthew Farrugia-Roberts , Liam Carroll , Susan Wei , Daniel Murfet

Training generative adversarial networks is unstable in high-dimensions as the true data distribution tends to be concentrated in a small fraction of the ambient space. The discriminator is then quickly able to classify nearly all generated…

Machine Learning · Computer Science 2018-06-26 Behnam Neyshabur , Srinadh Bhojanapalli , Ayan Chakrabarti

The lack of mathematical tractability of Deep Neural Networks (DNNs) has hindered progress towards having a unified convergence analysis of training algorithms, in the general setting. We propose a unified optimization framework for…

Machine Learning · Computer Science 2018-05-24 Hadi Ghauch , Hossein Shokri-Ghadikolaei , Carlo Fischione , Mikael Skoglund

The training of neural networks is a complex, high-dimensional, non-convex and noisy optimization problem whose theoretical understanding is interesting both from an applicative perspective and for fundamental reasons. A core challenge is…

Statistical Mechanics · Physics 2023-04-19 Theo Jules , Gal Brener , Tal Kachman , Noam Levi , Yohai Bar-Sinai

Neural networks, whice have had a profound effect on how researchers study complex phenomena, do so through a complex, nonlinear mathematical structure which can be difficult for human researchers to interpret. This obstacle can be…

Machine Learning · Computer Science 2024-06-18 Bradley T. Baker , Vince D. Calhoun , Sergey M. Plis

A key property of neural networks is their capacity of adapting to data during training. Yet, our current mathematical understanding of feature learning and its relationship to generalization remain limited. In this work, we provide a…

Machine Learning · Statistics 2024-10-25 Yatin Dandi , Luca Pesce , Hugo Cui , Florent Krzakala , Yue M. Lu , Bruno Loureiro

This work presents a novel means for understanding learning dynamics and scaling relations in neural networks. We show that certain measures on the spectrum of the empirical neural tangent kernel, specifically entropy and trace, yield…

Machine Learning · Computer Science 2024-10-11 Samuel Tovey , Sven Krippendorf , Michael Spannowsky , Konstantin Nikolaou , Christian Holm