English
Related papers

Related papers: Emergent Low-Rank Training Dynamics in MLPs with S…

200 papers

We study how neural networks trained by gradient descent extrapolate, i.e., what they learn outside the support of the training distribution. Previous works report mixed empirical results when extrapolating with neural networks: while…

Machine Learning · Computer Science 2021-03-04 Keyulu Xu , Mozhi Zhang , Jingling Li , Simon S. Du , Ken-ichi Kawarabayashi , Stefanie Jegelka

We describe a novel family of models of multi- layer feedforward neural networks in which the activation functions are encoded via penalties in the training problem. Our approach is based on representing a non-decreasing activation function…

Machine Learning · Computer Science 2018-06-22 Armin Askari , Geoffrey Negiar , Rajiv Sambharya , Laurent El Ghaoui

Large-scale deep neural networks consume expensive training costs, but the training results in less-interpretable weight matrices constructing the networks. Here, we propose a mode decomposition learning that can interpret the weight…

Machine Learning · Computer Science 2023-04-13 Chan Li , Haiping Huang

Low-rank compression, a popular model compression technique that produces compact convolutional neural networks (CNNs) with low rankness, has been well-studied in the literature. On the other hand, low-rank training, as an alternative way…

Computer Vision and Pattern Recognition · Computer Science 2024-01-22 Yang Sui , Miao Yin , Yu Gong , Jinqi Xiao , Huy Phan , Bo Yuan

We present a data-driven dimensionality reduction method that is well-suited for physics-based data representing hyperbolic wave propagation. The method utilizes a specialized neural network architecture called low rank neural…

Machine Learning · Computer Science 2025-11-05 Woojin Cho , Kookjin Lee , Noseong Park , Donsub Rim , Gerrit Welper

Modern neural networks are usually highly over-parameterized. Behind the wide usage of over-parameterized networks is the belief that, if the data are simple, then the trained network will be automatically equivalent to a simple predictor.…

Machine Learning · Statistics 2025-04-14 Chenyang Zhang , Peifeng Gao , Difan Zou , Yuan Cao

Epoch-wise double descent is the phenomenon where generalisation performance improves beyond the point of overfitting, resulting in a generalisation curve exhibiting two descents under the course of learning. Understanding the mechanisms…

Machine Learning · Statistics 2024-09-20 Amanda Olmin , Fredrik Lindsten

Gradient-based neural network training traditionally enforces symmetry between forward and backward propagation, requiring activation functions to be differentiable (or sub-differentiable) and strictly monotonic in certain regions to…

Neural and Evolutionary Computing · Computer Science 2025-09-10 Luigi Troiano , Francesco Gissi , Vincenzo Benedetto , Genny Tortora

We prove linear convergence of gradient descent to a global optimum for the training of deep residual networks with constant layer width and smooth activation function. We show that if the trained weights, as a function of the layer index,…

Machine Learning · Computer Science 2023-01-26 Rama Cont , Alain Rossier , RenYuan Xu

We investigate the training dynamics of two-layer neural networks when learning multi-index target functions. We focus on multi-pass gradient descent (GD) that reuses the batches multiple times and show that it significantly changes the…

Machine Learning · Statistics 2024-09-06 Yatin Dandi , Emanuele Troiani , Luca Arnaboldi , Luca Pesce , Lenka Zdeborová , Florent Krzakala

A remarkable recent discovery in machine learning has been that deep neural networks can achieve impressive performance (in terms of both lower training error and higher generalization capacity) in the regime where they are massively…

Machine Learning · Computer Science 2020-03-03 Thanh V. Nguyen , Raymond K. W. Wong , Chinmay Hegde

Recent observations have advanced our understanding of the neural network optimization landscape, revealing the existence of (1) paths of high accuracy containing diverse solutions and (2) wider minima offering improved performance.…

Machine Learning · Computer Science 2021-09-14 Mitchell Wortsman , Maxwell Horton , Carlos Guestrin , Ali Farhadi , Mohammad Rastegari

We refine a recently-proposed class of local entropic loss functions by restricting the smoothening regularization to only a subset of weights. The new loss functions are referred to as partial local entropies. They can adapt to the…

Machine Learning · Computer Science 2021-04-14 Daniele Musso

We develop a theoretical framework that explains how discrete symbolic structures can emerge naturally from continuous neural network training dynamics. By lifting neural parameters to a measure space and modeling training as Wasserstein…

Machine Learning · Computer Science 2025-07-03 Peihao Wang , Zhangyang Wang

We investigate the inherent bias of Stochastic Gradient Descent (SGD) toward learning low-rank weight matrices during the training of deep neural networks. Our results demonstrate that training with mini-batch SGD and weight decay induces a…

Machine Learning · Computer Science 2024-10-22 Tomer Galanti , Zachary S. Siegel , Aparna Gupte , Tomaso Poggio

We develop a statistical mechanical approach based on the replica method to study the design space of deep and wide neural networks constrained to meet a large number of training data. Specifically, we analyze the configuration space of the…

Disordered Systems and Neural Networks · Physics 2020-04-17 Hajime Yoshino

Large language models are powerful but costly. We ask whether meta-learning can make the pretraining of small language models not only better but also more interpretable. We integrate first-order MAML with subset-masked LM pretraining,…

Computation and Language · Computer Science 2025-11-10 David Demitri Africa , Yuval Weiss , Paula Buttery , Richard Diehl Martinez

Despite many modern applications of Deep Neural Networks (DNNs), the large number of parameters in the hidden layers makes them unattractive for deployment on devices with storage capacity constraints. In this paper we propose a Data-Driven…

Machine Learning · Computer Science 2021-07-14 Dimitris Papadimitriou , Swayambhoo Jain

The remarkable capability of Transformers to do reasoning and few-shot learning, without any fine-tuning, is widely conjectured to stem from their ability to implicitly simulate a multi-step algorithms -- such as gradient descent -- with…

Machine Learning · Computer Science 2024-10-14 Khashayar Gatmiry , Nikunj Saunshi , Sashank J. Reddi , Stefanie Jegelka , Sanjiv Kumar

To theoretically understand the behavior of trained deep neural networks, it is necessary to study the dynamics induced by gradient methods from a random initialization. However, the nonlinear and compositional structure of these models…

Machine Learning · Computer Science 2021-12-21 Karl Hajjar , Lénaïc Chizat , Christophe Giraud
‹ Prev 1 8 9 10 Next ›