English
Related papers

Related papers: GradInit: Learning to Initialize Neural Networks f…

200 papers

A recent line of research has shown that gradient-based algorithms with random initialization can converge to the global minima of the training loss for over-parameterized (i.e., sufficiently wide) deep neural networks. However, the…

Machine Learning · Computer Science 2019-06-12 Difan Zou , Quanquan Gu

Port-Hamiltonian neural networks have shown promising results in the identification of nonlinear dynamics of complex systems, as their combination of physical principles with data-driven learning allows for accurate modelling. However, due…

Systems and Control · Electrical Eng. & Systems 2026-01-28 G. J. E. van Otterdijk , S. Weiland , M. Schoukens

We demonstrate that architectures which traditionally are considered to be ill-suited for a task can be trained using inductive biases from another architecture. We call a network untrainable when it overfits, underfits, or converges to…

Machine Learning · Computer Science 2025-10-27 Vighnesh Subramaniam , David Mayo , Colin Conwell , Tomaso Poggio , Boris Katz , Brian Cheung , Andrei Barbu

The recent advent of automated neural network architecture search led to several methods that outperform state-of-the-art human-designed architectures. However, these approaches are computationally expensive, in extreme cases consuming GPU…

Machine Learning · Computer Science 2019-03-11 Martin Wistuba , Tejaswini Pedapati

The stochastic gradient descent (SGD) algorithm has achieved remarkable success in training deep learning models. However, it has several limitations, including susceptibility to vanishing gradients, sensitivity to input data, and a lack of…

Machine Learning · Computer Science 2025-03-14 Chengcheng Yan , Jiawei Xu , Qingsong Wang , Zheng Peng

Network pruning is a promising avenue for compressing deep neural networks. A typical approach to pruning starts by training a model and then removing redundant parameters while minimizing the impact on what is learned. Alternatively, a…

Machine Learning · Computer Science 2020-02-18 Namhoon Lee , Thalaiyasingam Ajanthan , Stephen Gould , Philip H. S. Torr

Recently many first and second order variants of SGD have been proposed to facilitate training of Deep Neural Networks (DNNs). A common limitation of these works stem from the fact that they use the same learning rate across all instances…

Machine Learning · Computer Science 2021-05-31 Shreyas Saxena , Nidhi Vyas , Dennis DeCoste

Natural gradient descent (NGD) is a powerful optimization technique for machine learning, but the computational complexity of the inverse Fisher information matrix limits its application in training deep neural networks. To overcome this…

Machine Learning · Computer Science 2024-12-11 Weihua Liu , Said Boumaraf , Jianwu Li , Chaochao Lin , Xiabi Liu , Lijuan Niu , Naoufel Werghi

This paper investigates the problem of recovering hyperspectral (HS) images from single RGB images. To tackle such a severely ill-posed problem, we propose a physically-interpretable, compact, efficient, and end-to-end learning-based…

Image and Video Processing · Electrical Eng. & Systems 2021-08-29 Zhiyu Zhu , Hui Liu , Junhui Hou , Sen Jia , Qingfu Zhang

We propose a simple, data-driven approach to help guide hyperparameter selection for neural network initialization. We leverage the relationship between neural network and Gaussian process models having corresponding activation and…

Machine Learning · Statistics 2020-12-21 Anthony S. Tai , Chunfeng Huang

Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety. Machine unlearning seeks to remove the influence of a targeted forget set while preserving model…

While the expressive power and computational capabilities of graph neural networks (GNNs) have been theoretically studied, their optimization and learning dynamics, in general, remain largely unexplored. Our study undertakes the Graph…

Machine Learning · Computer Science 2023-10-26 Nimrah Mustafa , Aleksandar Bojchevski , Rebekka Burkholz

The training of machine learning models is typically carried out using some form of gradient descent, often with great success. However, non-asymptotic analyses of first-order optimization algorithms typically employ a gradient smoothness…

Machine Learning · Computer Science 2024-06-18 Thomas Flynn

Modern neural networks are typically trained in an over-parameterized regime where the parameters of the model far exceed the size of the training data. Such neural networks in principle have the capacity to (over)fit any set of labels…

Machine Learning · Computer Science 2019-07-05 Mingchen Li , Mahdi Soltanolkotabi , Samet Oymak

We introduce AlphaGrad, a memory-efficient, conditionally stateless optimizer addressing the memory overhead and hyperparameter complexity of adaptive methods like Adam. AlphaGrad enforces scale invariance via tensor-wise L2 gradient…

Machine Learning · Computer Science 2025-04-24 Soham Sane

This paper introduces the notion of ``Initial Alignment'' (INAL) between a neural network at initialization and a target function. It is proved that if a network and a Boolean target function do not have a noticeable INAL, then noisy…

Machine Learning · Computer Science 2022-08-17 Emmanuel Abbe , Elisabetta Cornacchia , Jan Hązła , Christopher Marquis

Many modern learning tasks involve fitting nonlinear models to data which are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Due to this overparameterization, the training…

Machine Learning · Computer Science 2018-12-27 Samet Oymak , Mahdi Soltanolkotabi

Plasticity loss, a critical challenge in neural network training, limits a model's ability to adapt to new tasks or shifts in data distribution. This paper introduces AID (Activation by Interval-wise Dropout), a novel method inspired by…

Machine Learning · Computer Science 2025-06-24 Sangyeon Park , Isaac Han , Seungwon Oh , Kyung-Joong Kim

The early phase of training of deep neural networks is critical for their final performance. In this work, we study how the hyperparameters of stochastic gradient descent (SGD) used in the early phase of training affect the rest of the…

Machine Learning · Computer Science 2020-02-25 Stanislaw Jastrzebski , Maciej Szymczak , Stanislav Fort , Devansh Arpit , Jacek Tabor , Kyunghyun Cho , Krzysztof Geras

Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates…

Machine Learning · Computer Science 2015-03-03 Sergey Ioffe , Christian Szegedy