English
Related papers

Related papers: Why is Normalization Preferred? A Worst-Case Compl…

200 papers

Local SGD is a communication-efficient variant of SGD for large-scale training, where multiple GPUs perform SGD independently and average the model parameters periodically. It has been recently observed that Local SGD can not only achieve…

Machine Learning · Computer Science 2023-03-10 Xinran Gu , Kaifeng Lyu , Longbo Huang , Sanjeev Arora

The gradient noise (GN) in the stochastic gradient descent (SGD) algorithm is often considered to be Gaussian in the large data regime by assuming that the classical central limit theorem (CLT) kicks in. This assumption is often made for…

Machine Learning · Computer Science 2019-01-21 Umut Simsekli , Levent Sagun , Mert Gurbuzbalaban

This paper studies the convergence of clipped stochastic gradient descent (SGD) algorithms with decision-dependent data distribution. Our setting is motivated by privacy preserving optimization algorithms that interact with performative…

Optimization and Control · Mathematics 2025-01-31 Qiang Li , Michal Yemini , Hoi-To Wai

Adaptive optimization algorithms, such as Adam and RMSprop, have shown better optimization performance than stochastic gradient descent (SGD) in some scenarios. However, recent studies show that they often lead to worse generalization…

Machine Learning · Computer Science 2018-09-19 Zijun Zhang , Lin Ma , Zongpeng Li , Chuan Wu

We present a novel approach to accelerate stochastic gradient descent (SGD) by utilizing curvature information obtained from Hessian-vector products or finite differences of parameters and gradients, similar to the BFGS algorithm. Our…

Machine Learning · Computer Science 2024-02-08 Omead Pooladzandi , Xi-Lin Li

It is not clear yet why ADAM-alike adaptive gradient algorithms suffer from worse generalization performance than SGD despite their faster training speed. This work aims to provide understandings on this generalization gap by analyzing…

Machine Learning · Computer Science 2021-11-30 Pan Zhou , Jiashi Feng , Chao Ma , Caiming Xiong , Steven Hoi , Weinan E

Per-example gradient clipping is a key algorithmic step that enables practical differential private (DP) training for deep learning models. The choice of clipping threshold R, however, is vital for achieving high accuracy under DP. We…

Machine Learning · Computer Science 2023-10-05 Zhiqi Bu , Yu-Xiang Wang , Sheng Zha , George Karypis

In this paper, we consider nonlinear optimization problems with a stochastic objective and deterministic equality constraints. We propose a Trust-Region Stochastic Sequential Quadratic Programming (TR-SSQP) method and establish its…

Optimization and Control · Mathematics 2026-04-02 Yuchen Fang , Javad Lavaei , Sen Na

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

Stochastic gradient descent is one of the most successful approaches for solving large-scale problems, especially in machine learning and statistics. At each iteration, it employs an unbiased estimator of the full gradient computed from one…

Numerical Analysis · Mathematics 2018-12-05 Bangti Jin , Xiliang Lu

Generalization is one of the most important problems in deep learning (DL). In the overparameterized regime in neural networks, there exist many low-loss solutions that fit the training data equally well. The key question is which solution…

Disordered Systems and Neural Networks · Physics 2023-06-21 Ning Yang , Chao Tang , Yuhai Tu

Distributed optimization plays an important role in modern large-scale machine learning and data processing systems by optimizing the utilization of computational resources. One of the classical and popular approaches is Local Stochastic…

Optimization and Control · Mathematics 2024-12-19 Andrey Sadchikov , Savelii Chezhegov , Aleksandr Beznosikov , Alexander Gasnikov

A central requirement for the acceptance of machine learning methods for human-centric tasks is that they should be fair, in the sense that they should work comparably well for individuals from different societal groups. A second, equally…

Machine Learning · Computer Science 2026-05-28 Max Cairney-Leeming , Amartya Sanyal , Christoph H. Lampert

In this paper, we utilize stochastic optimization to reduce the space complexity of convex composite optimization with a nuclear norm regularizer, where the variable is a matrix of size $m \times n$. By constructing a low-rank estimate of…

Machine Learning · Computer Science 2015-12-08 Lijun Zhang , Tianbao Yang , Rong Jin , Zhi-Hua Zhou

Stochastic gradient descent (SGD) and adaptive gradient methods, such as Adam and RMSProp, have been widely used in training deep neural networks. We empirically show that while the difference between the standard generalization performance…

Machine Learning · Computer Science 2023-11-30 Avery Ma , Yangchen Pan , Amir-massoud Farahmand

In this paper, we study the convergence properties of the Stochastic Gradient Descent (SGD) method for finding a stationary point of a given objective function $J(\cdot)$. The objective function is not required to be convex. Rather, our…

Machine Learning · Statistics 2024-09-24 Rajeeva L. Karandikar , M. Vidyasagar

Stochastic gradient descent (SGD) is a promising numerical method for solving large-scale inverse problems. However, its theoretical properties remain largely underexplored in the lens of classical regularization theory. In this note, we…

Numerical Analysis · Mathematics 2020-07-22 Tim Jahn , Bangti Jin

The representation of functions by artificial neural networks depends on a large number of parameters in a non-linear fashion. Suitable parameters of these are found by minimizing a 'loss functional', typically by stochastic gradient…

Machine Learning · Computer Science 2021-09-16 Stephan Wojtowytsch

It has repeatedly been observed that loss minimization by stochastic gradient descent (SGD) leads to heavy-tailed distributions of neural network parameters. Here, we analyze a continuous diffusion approximation of SGD, called homogenized…

Machine Learning · Statistics 2024-02-05 Zhe Jiao , Martin Keller-Ressel

While stochastic gradient descent (SGD) is still the most popular optimization algorithm in deep learning, adaptive algorithms such as Adam have established empirical advantages over SGD in some deep learning applications such as training…

Machine Learning · Computer Science 2023-06-02 Yan Pan , Yuanzhi Li