English
Related papers

Related papers: Effect of Depth and Width on Local Minima in Deep …

200 papers

We investigate the loss surface of neural networks. We prove that even for one-hidden-layer networks with "slightest" nonlinearity, the empirical risks have spurious local minima in most cases. Our results thus indicate that in general "no…

Machine Learning · Computer Science 2019-05-29 Chulhee Yun , Suvrit Sra , Ali Jadbabaie

The infrequent occurrence of overfitting in deep neural networks is perplexing: contrary to theoretical expectations, increasing model size often enhances performance in practice. But what if overfitting does occur, though restricted to…

Machine Learning · Computer Science 2025-01-08 Uri Stern , Tomer Yaacoby , Daphna Weinshall

We propose to impose symmetry in neural network parameters to improve parameter usage and make use of dedicated convolution and matrix multiplication routines. Due to significant reduction in the number of parameters as a result of the…

Machine Learning · Computer Science 2019-01-11 Xu Shell Hu , Sergey Zagoruyko , Nikos Komodakis

It has been recognized that heavily overparameterized deep neural networks (DNNs) exhibit surprisingly good generalization performance in various machine-learning tasks. Although benefits of depth have been investigated from different…

Machine Learning · Computer Science 2022-01-31 Takashi Mori , Masahito Ueda

Under mild assumptions, we investigate the geometry of the loss landscape for two-layer neural networks in the vicinity of global minima. Utilizing novel techniques, we demonstrate: (i) how global minima with zero generalization error…

Machine Learning · Computer Science 2025-04-11 Leyang Zhang , Yaoyu Zhang , Tao Luo

In this paper, we theoretically prove that gradient descent can find a global minimum of non-convex optimization of all layers for nonlinear deep neural networks of sizes commonly encountered in practice. The theory developed in this paper…

Machine Learning · Statistics 2020-06-18 Kenji Kawaguchi , Jiaoyang Huang

We theoretically characterize gradient descent dynamics in deep linear networks trained at large width from random initialization and on large quantities of random data. Our theory captures the ``wider is better" effect of…

Machine Learning · Computer Science 2025-06-17 Blake Bordelon , Cengiz Pehlevan

Recent work has found that neural networks with stronger generalization tend to exhibit higher representational alignment with one another across architectures and training paradigms. In this work, we show that models with stronger…

Machine Learning · Computer Science 2026-02-02 Junjie Yu , Wenxiao Ma , Chen Wei , Jianyu Zhang , Haotian Deng , Zihan Deng , Quanying Liu

Deep state-space models (SSMs) have gained increasing popularity in sequence modelling. While there are numerous theoretical investigations of shallow SSMs, how the depth of the SSM affects its expressiveness remains a crucial problem. In…

Machine Learning · Computer Science 2025-06-25 Zeyu Bao , Penghao Yu , Haotian Jiang , Qianxiao Li

A recent line of research on deep learning focuses on the extremely over-parameterized setting, and shows that when the network width is larger than a high degree polynomial of the training sample size $n$ and the inverse of the target…

Machine Learning · Computer Science 2022-01-03 Zixiang Chen , Yuan Cao , Difan Zou , Quanquan Gu

Neural networks trained via gradient descent with random initialization and without any regularization enjoy good generalization performance in practice despite being highly overparametrized. A promising direction to explain this phenomenon…

Machine Learning · Computer Science 2022-05-17 Hancheng Min , Salma Tarmoun , Rene Vidal , Enrique Mallada

Sharpness-Aware Minimization (SAM) has attracted considerable attention for its effectiveness in improving generalization in deep neural network training by explicitly minimizing sharpness in the loss landscape. Its success, however, relies…

Machine Learning · Computer Science 2025-06-16 Sungbin Shin , Dongyeop Lee , Maksym Andriushchenko , Namhoon Lee

Traditional deep network training methods optimize a monolithic objective function jointly for all the components. This can lead to various inefficiencies in terms of potential parallelization. Local learning is an approach to…

Machine Learning · Computer Science 2023-01-19 Adeetya Patel , Michael Eickenberg , Eugene Belilovsky

We study the effect of width on the dynamics of feature-learning neural networks across a variety of architectures and datasets. Early in training, wide neural networks trained on online data have not only identical loss curves but also…

Machine Learning · Computer Science 2023-12-07 Nikhil Vyas , Alexander Atanasov , Blake Bordelon , Depen Morwani , Sabarish Sainathan , Cengiz Pehlevan

The cost of hyperparameter tuning in deep learning has been rising with model sizes, prompting practitioners to find new tuning methods using a proxy of smaller networks. One such proposal uses $\mu$P parameterized networks, where the…

Machine Learning · Statistics 2023-12-11 Blake Bordelon , Lorenzo Noci , Mufan Bill Li , Boris Hanin , Cengiz Pehlevan

We study the role of depth in training randomly initialized overparameterized neural networks. We give a general result showing that depth improves trainability of neural networks by improving the conditioning of certain kernel matrices of…

Machine Learning · Computer Science 2021-02-18 Naman Agarwal , Pranjal Awasthi , Satyen Kale

In this paper, we prove a conjecture published in 1989 and also partially address an open problem announced at the Conference on Learning Theory (COLT) 2015. With no unrealistic assumption, we first prove the following statements for the…

Machine Learning · Statistics 2016-12-30 Kenji Kawaguchi

We study the average robustness notion in deep neural networks in (selected) wide and narrow, deep and shallow, as well as lazy and non-lazy training settings. We prove that in the under-parameterized setting, width has a negative effect…

Machine Learning · Computer Science 2023-02-13 Zhenyu Zhu , Fanghui Liu , Grigorios G Chrysos , Volkan Cevher

Practitioners prune neural networks for efficiency gains and generalization improvements, but few scrutinize the factors determining the prunability of a neural network the maximum fraction of weights that pruning can remove without…

Machine Learning · Computer Science 2022-12-02 Zachary Ankner , Alex Renda , Gintare Karolina Dziugaite , Jonathan Frankle , Tian Jin

The selection of initial parameter values for gradient-based optimization of deep neural networks is one of the most impactful hyperparameter choices in deep learning systems, affecting both convergence times and model performance. Yet…

Machine Learning · Computer Science 2020-01-17 Wei Hu , Lechao Xiao , Jeffrey Pennington