English
Related papers

Related papers: Implicit regularization in Heavy-ball momentum acc…

200 papers

In this paper, we provide a comprehensive theoretical analysis of Stochastic Gradient Descent (SGD) and its momentum variants (Polyak Heavy-Ball and Nesterov) for tracking time-varying optima under strong convexity and smoothness. Our…

Machine Learning · Statistics 2026-05-20 Sharan Sahu , Cameron J. Hogan , Martin T. Wells

We study gradient flow on the exponential loss for a classification problem with a one-layer softmax attention model, where the key and query weight matrices are trained separately. Under a separability assumption on the data, we show that…

Machine Learning · Computer Science 2024-03-14 Heejune Sheen , Siyu Chen , Tianhao Wang , Harrison H. Zhou

In overparameterized logistic regression, gradient descent (GD) iterates diverge in norm while converging in direction to the maximum $\ell_2$-margin solution -- a phenomenon known as the implicit bias of GD. This work investigates…

Machine Learning · Computer Science 2025-07-01 Jingfeng Wu , Peter Bartlett , Matus Telgarsky , Bin Yu

We study implicit regularization when optimizing an underdetermined quadratic objective over a matrix $X$ with gradient descent on a factorization of $X$. We conjecture and provide empirical and theoretical evidence that with small enough…

Machine Learning · Statistics 2017-05-26 Suriya Gunasekar , Blake Woodworth , Srinadh Bhojanapalli , Behnam Neyshabur , Nathan Srebro

Stochastic gradient descent (SGD) is almost ubiquitously used for training non-convex optimization tasks. Recently, a hypothesis proposed by Keskar et al. [2017] that large batch methods tend to converge to sharp minimizers has received…

Machine Learning · Statistics 2018-12-04 Xiaowu Dai , Yuhua Zhu

Attempts of studying implicit regularization associated to gradient descent (GD) have identified matrix completion as a suitable test-bed. Late findings suggest that this phenomenon cannot be phrased as a minimization-norm problem, implying…

Artificial Intelligence · Computer Science 2021-05-05 Paolo Milanesi , Hachem Kadri , Stéphane Ayache , Thierry Artières

Multi-epoch, small-batch, Stochastic Gradient Descent (SGD) has been the method of choice for learning with large over-parameterized models. A popular theory for explaining why SGD works well in practice is that the algorithm has an…

Machine Learning · Computer Science 2021-07-13 Satyen Kale , Ayush Sekhari , Karthik Sridharan

The (stochastic) gradient descent and the multiplicative update method are probably the most popular algorithms in machine learning. We introduce and study a new regularization which provides a unification of the additive and multiplicative…

Machine Learning · Computer Science 2019-02-07 Udaya Ghai , Elad Hazan , Yoram Singer

Momentum is known to accelerate the convergence of gradient descent in strongly convex settings without stochastic gradient noise. In stochastic optimization, such as training neural networks, folklore suggests that momentum may help deep…

Machine Learning · Computer Science 2024-04-17 Runzhe Wang , Sadhika Malladi , Tianhao Wang , Kaifeng Lyu , Zhiyuan Li

Since Polyak's pioneering work, heavy ball (HB) momentum has been widely studied in minimization. However, its role in min-max games remains largely unexplored. As a key component of practical min-max algorithms like Adam, this gap limits…

Computer Science and Game Theory · Computer Science 2025-05-27 Yi Feng , Kaito Fujii , Stratis Skoulakis , Xiao Wang , Volkan Cevher

It is important to understand how dropout, a popular regularization method, aids in achieving a good generalization solution during neural network training. In this work, we present a theoretical derivation of an implicit regularization of…

Machine Learning · Computer Science 2023-04-11 Zhongwang Zhang , Zhi-Qin John Xu

In previous literature, backward error analysis was used to find ordinary differential equations (ODEs) approximating the gradient descent trajectory. It was found that finite step sizes implicitly regularize solutions because terms…

Machine Learning · Computer Science 2024-06-18 Matias D. Cattaneo , Jason M. Klusowski , Boris Shigida

We establish the asymptotic implicit bias of gradient descent (GD) for generic non-homogeneous deep networks under exponential loss. Specifically, we characterize three key properties of GD iterates starting from a sufficiently small…

Machine Learning · Computer Science 2025-07-17 Yuhang Cai , Kangjie Zhou , Jingfeng Wu , Song Mei , Michael Lindsey , Peter L. Bartlett

Understanding the implicit bias of Stochastic Gradient Descent (SGD) is one of the key challenges in deep learning, especially for overparametrized models, where the local minimizers of the loss function $L$ can form a manifold.…

Machine Learning · Computer Science 2022-07-29 Zhiyuan Li , Tianhao Wang , Sanjeev Arora

Normalization techniques are a boon for modern deep learning. They let weights converge more quickly with often better generalization performances. It has been argued that the normalization-induced scale invariance among the weights…

Machine Learning · Computer Science 2021-01-19 Byeongho Heo , Sanghyuk Chun , Seong Joon Oh , Dongyoon Han , Sangdoo Yun , Gyuwan Kim , Youngjung Uh , Jung-Woo Ha

We analyze the sample complexity of full-batch Gradient Descent (GD) in the setup of non-smooth Stochastic Convex Optimization. We show that the generalization error of GD, with common choice of hyper-parameters, can be $\tilde \Theta(d/m +…

Machine Learning · Computer Science 2024-04-12 Roi Livni

Even for the gradient descent (GD) method applied to neural network training, understanding its optimization dynamics, including convergence rate, iterate trajectories, function value oscillations, and especially its implicit acceleration,…

Machine Learning · Computer Science 2026-05-22 Alexander Tyurin

Numerous empirical evidences have corroborated the importance of noise in nonconvex optimization problems. The theory behind such empirical observations, however, is still largely unknown. This paper studies this fundamental problem through…

Machine Learning · Computer Science 2021-02-25 Tianyi Liu , Yan Li , Song Wei , Enlu Zhou , Tuo Zhao

The simplicity of gradient descent (GD) made it the default method for training ever-deeper and complex neural networks. Both loss functions and architectures are often explicitly tuned to be amenable to this basic local optimization. In…

Machine Learning · Computer Science 2019-04-30 Dmitrii Marin , Meng Tang , Ismail Ben Ayed , Yuri Boykov

We analyze the training dynamics for deep linear networks using a new metric - layer imbalance - which defines the flatness of a solution. We demonstrate that different regularization methods, such as weight decay or noise data…

Machine Learning · Computer Science 2020-07-21 Boris Ginsburg