English
Related papers

Related papers: Implicit Regularization and Convergence for Weight…

200 papers

Merging models becomes a fundamental procedure in some applications that consider model efficiency and robustness. The training randomness or Non-I.I.D. data poses a huge challenge for averaging-based model fusion. Previous research efforts…

Artificial Intelligence · Computer Science 2024-08-23 Yichu Xu , Xin-Chun Li , Le Gan , De-Chuan Zhan

Despite the simplicity, stochastic gradient descent (SGD)-like algorithms are successful in training deep neural networks (DNNs). Among various attempts to improve SGD, weight averaging (WA), which averages the weights of multiple models,…

Machine Learning · Computer Science 2023-04-25 Xiaozhe Gu , Zixun Zhang , Yuncheng Jiang , Tao Luo , Ruimao Zhang , Shuguang Cui , Zhen Li

Recent works have shown that on sufficiently over-parametrized neural nets, gradient descent with relatively large initialization optimizes a prediction function in the RKHS of the Neural Tangent Kernel (NTK). This analysis leads to global…

Machine Learning · Statistics 2020-04-28 Colin Wei , Jason D. Lee , Qiang Liu , Tengyu Ma

Optimization problem, which is aimed at finding the global minimal value of a given cost function, is one of the central problem in science and engineering. Various numerical methods have been proposed to solve this problem, among which the…

Optimization and Control · Mathematics 2022-10-07 Shaojun Dong , Fengyu Le , Meng Zhang , Si-Jing Tao , Chao Wang , Yong-Jian Han , Guo-Ping Guo

Stochastic gradient descent (SGD) has been the dominant optimization method for training deep neural networks due to its many desirable properties. One of the more remarkable and least understood quality of SGD is that it generalizes…

Machine Learning · Computer Science 2020-07-03 Erhan Bilal

This paper explores the problem of generalized phase retrieval, which involves reconstructing a length-$n$ signal $\bm{x}$ from its $m$ phaseless samples $y_k = \left|\langle \bm{a}_k,\bm{x}\rangle\right|^2$, where $k = 1,2,...,m$, and…

Information Theory · Computer Science 2026-04-16 Jianfeng Cai , Huiping Li , Jiayi Li

Recent works have highlighted scale invariance or symmetry present in the weight space of a typical deep network and the adverse effect it has on the Euclidean gradient based stochastic gradient descent optimization. In this work, we show…

Machine Learning · Computer Science 2015-11-04 Vijay Badrinarayanan , Bamdev Mishra , Roberto Cipolla

We introduce new multilevel methods for solving large-scale unconstrained optimization problems. Specifically, the philosophy of multilevel methods is applied to Newton-type methods that regularize the Newton sub-problem using second order…

Optimization and Control · Mathematics 2024-07-16 Nick Tsipinakis , Panos Parpas

We propose a general learning based framework for solving nonsmooth and nonconvex image reconstruction problems. We model the regularization function as the composition of the $l_{2,1}$ norm and a smooth but nonconvex feature mapping…

Computer Vision and Pattern Recognition · Computer Science 2022-09-07 Yunmei Chen , Hongcheng Liu , Xiaojing Ye , Qingchao Zhang

We obtain an improved finite-sample guarantee on the linear convergence of stochastic gradient descent for smooth and strongly convex objectives, improving from a quadratic dependence on the conditioning $(L/\mu)^2$ (where $L$ is a bound on…

Numerical Analysis · Mathematics 2015-01-19 Deanna Needell , Nathan Srebro , Rachel Ward

A widely believed explanation for the remarkable generalization capacities of overparameterized neural networks is that the optimization algorithms used for training induce an implicit bias towards benign solutions. To grasp this…

Machine Learning · Computer Science 2025-12-19 Maria Matveev , Vit Fojtik , Hung-Hsu Chou , Gitta Kutyniok , Johannes Maly

We are concerned with the convergence of NEAR-DGD$^+$ (Nested Exact Alternating Recursion Distributed Gradient Descent) method introduced to solve the distributed optimization problems. Under the assumption of the strong convexity of local…

Optimization and Control · Mathematics 2022-06-28 Woocheol Choi , Doheon Kim , Seok-Bae Yun

Stochastic Gradient Descent (SGD) is one of the most popular algorithms in statistical and machine learning due to its computational and memory efficiency. Various averaging schemes have been proposed to accelerate the convergence of SGD in…

Machine Learning · Statistics 2025-04-08 Ziyang Wei , Wanrong Zhu , Wei Biao Wu

Optimization algorithms for solving nonconvex inverse problem have attracted significant interests recently. However, existing methods require the nonconvex regularization to be smooth or simple to ensure convergence. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2020-03-26 Qingchao Zhang , Xiaojing Ye , Hongcheng Liu , Yunmei Chen

Using weight decay to penalize the L2 norms of weights in neural networks has been a standard training practice to regularize the complexity of networks. In this paper, we show that a family of regularizers, including weight decay, is…

Machine Learning · Computer Science 2022-06-09 Ziquan Liu , Yufei Cui , Antoni B. Chan

Weight play an essential role in deep learning network models. Unlike network structure design, this article proposes the concept of weight augmentation, focusing on weight exploration. The core of Weight Augmentation Strategy (WAS) is to…

Machine Learning · Computer Science 2024-05-31 Junbin Zhuang , Guiguang Din , Yunyi Yan

Adaptive gradient methods like AdaGrad are widely used in optimizing neural networks. Yet, existing convergence guarantees for adaptive gradient methods require either convexity or smoothness, and, in the smooth setting, only guarantee…

Machine Learning · Computer Science 2019-10-22 Xiaoxia Wu , Simon S. Du , Rachel Ward

Wasserstein distributionally robust optimization offers a framework for model fitting in machine learning under potential shifts in the data distribution. We study a regularized variant of this problem in which entropic smoothing produces a…

Optimization and Control · Mathematics 2026-05-28 Tam Le

One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can achieve zero training loss even though the objective function is non-convex and non-smooth. This paper demystifies…

Machine Learning · Computer Science 2019-02-06 Simon S. Du , Xiyu Zhai , Barnabas Poczos , Aarti Singh

Regularization is commonly used for alleviating overfitting in machine learning. For convolutional neural networks (CNNs), regularization methods, such as DropBlock and Shake-Shake, have illustrated the improvement in the generalization…

Computer Vision and Pattern Recognition · Computer Science 2021-01-01 Yi Wang , Zhen-Peng Bian , Junhui Hou , Lap-Pui Chau