English
Related papers

Related papers: On the Loss Landscape Geometry of Regularized Deep…

200 papers

The pursuit of explaining and improving generalization in deep learning has elicited efforts both in regularization techniques as well as visualization techniques of the loss surface geometry. The latter is related to the intuition…

Machine Learning · Computer Science 2019-07-23 Vinay Uday Prabhu , Dian Ang Yap , Joyce Xu , John Whaley

Training deep neural networks with stochastic gradient descent (SGD) can often achieve zero training loss on real-world tasks although the optimization landscape is known to be highly non-convex. To understand the success of SGD for…

Machine Learning · Statistics 2020-06-15 Yiping Lu , Chao Ma , Yulong Lu , Jianfeng Lu , Lexing Ying

Quantization-Aware Training (QAT) is one of the prevailing neural network compression solutions. However, its stability has been challenged for yielding deteriorating performances as the quantization error is inevitable. We find that the…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Junbiao Pang , Tianyang Cai

Understanding the curvature evolution of the loss landscape is fundamental to analyzing the training dynamics of neural networks. The most commonly studied measure, Hessian sharpness ($\lambda_{\max}^H$) -- the largest eigenvalue of the…

We study the loss surface of DNNs with $L_{2}$ regularization. We show that the loss in terms of the parameters can be reformulated into a loss in terms of the layerwise activations $Z_{\ell}$ of the training set. This reformulation reveals…

Machine Learning · Statistics 2022-10-17 Arthur Jacot , Eugene Golikov , Clément Hongler , Franck Gabriel

This work characterizes the effect of depth on the optimization landscape of linear regression, showing that, despite their nonconvexity, deeper models have more desirable optimization landscape. We consider a robust and over-parameterized…

Machine Learning · Computer Science 2022-07-18 Jianhao Ma , Salar Fattahi

Regularization is essential when training large neural networks. As deep neural networks can be mathematically interpreted as universal function approximators, they are effective at memorizing sampling noise in the training data. This…

Machine Learning · Computer Science 2015-01-06 Jan Rudy , Weiguang Ding , Daniel Jiwoong Im , Graham W. Taylor

Neural networks that land in flat regions of the loss landscape tend to generalise better than those in sharp regions. Sharpness-Aware Minimisation exploits this to improve generalisation. But function-preserving reparameterisation can…

Machine Learning · Computer Science 2026-05-08 Michael Timothy Bennett

We explore the low-rank structure of the weight matrices in neural networks at the stationary points (limiting solutions of optimization algorithms) with $L2$ regularization (also known as weight decay). We show several properties of such…

Machine Learning · Computer Science 2025-08-21 Ilja Kuzborskij , Yasin Abbasi Yadkori

We analyze the loss landscape and expressiveness of practical deep convolutional neural networks (CNNs) with shared weights and max pooling layers. We show that such CNNs produce linearly independent features at a "wide" layer which has…

Machine Learning · Computer Science 2018-06-07 Quynh Nguyen , Matthias Hein

We prove a general Embedding Principle of loss landscape of deep neural networks (NNs) that unravels a hierarchical structure of the loss landscape of NNs, i.e., loss landscape of an NN contains all critical points of all the narrower NNs.…

Machine Learning · Computer Science 2021-12-01 Yaoyu Zhang , Yuqing Li , Zhongwang Zhang , Tao Luo , Zhi-Qin John Xu

Near an optimal learning point of a neural network, the learning performance of gradient descent dynamics is dictated by the Hessian matrix of the loss function with respect to the network parameters. We characterize the Hessian…

Machine Learning · Statistics 2025-12-18 Carlos Couto , José Mourão , Mário A. T. Figueiredo , Pedro Ribeiro

We present a Gaussian kernel loss function and training algorithm for convolutional neural networks that can be directly applied to both distance metric learning and image classification problems. Our method treats all training features…

Computer Vision and Pattern Recognition · Computer Science 2018-07-03 Benjamin J. Meyer , Ben Harwood , Tom Drummond

When training overparameterized deep networks for classification tasks, it has been widely observed that the learned features exhibit a so-called "neural collapse" phenomenon. More specifically, for the output features of the penultimate…

Machine Learning · Computer Science 2023-03-09 Can Yaras , Peng Wang , Zhihui Zhu , Laura Balzano , Qing Qu

We analyze single-layer neural networks with the Xavier initialization in the asymptotic regime of large numbers of hidden units and large numbers of stochastic gradient descent training steps. The evolution of the neural network during…

Probability · Mathematics 2022-04-13 Justin Sirignano , Konstantinos Spiliopoulos

We consider a high-probability non-asymptotic confidence estimation in the $\ell^2$-regularized non-linear least-squares setting with fixed design. In particular, we study confidence estimation for local minimizers of the regularized…

Machine Learning · Computer Science 2025-06-12 Ilja Kuzborskij , Yasin Abbasi Yadkori

In the matrix sensing problem, one wishes to reconstruct a matrix from (possibly noisy) observations of its linear projections along given directions. We consider this model in the high-dimensional limit: while previous works on this model…

Machine Learning · Statistics 2025-11-13 Yizhou Xu , Antoine Maillard , Lenka Zdeborová , Florent Krzakala

LU and Cholesky matrix factorization algorithms are core subroutines used to solve systems of linear equations (SLEs) encountered while solving an optimization problem. Standard factorization algorithms are highly efficient but remain…

Numerical Analysis · Mathematics 2022-07-25 Adolfo R. Escobedo

A main puzzle of deep networks revolves around the absence of overfitting despite large overparametrization and despite the large capacity demonstrated by zero training error on randomly labeled data. In this note, we show that the dynamics…

Loss of plasticity, trainability loss, and primacy bias have been identified as issues arising when training deep neural networks on sequences of tasks -- all referring to the increased difficulty in training on new tasks. We propose to use…

Machine Learning · Computer Science 2024-12-11 Wesley Chung , Lynn Cherif , David Meger , Doina Precup
‹ Prev 1 4 5 6 7 8 10 Next ›