English
Related papers

Related papers: Second-order Optimization under Heavy-Tailed Noise…

200 papers

Hierarchical optimization refers to problems with interdependent decision variables and objectives, such as minimax and bilevel formulations. While various algorithms have been proposed, existing methods and analyses lack adaptivity in…

Machine Learning · Computer Science 2025-10-27 Xiaochuan Gong , Jie Hao , Mingrui Liu

Conventional de-noising methods rely on the assumption that all samples are independent and identically distributed, so the resultant classifier, though disturbed by noise, can still easily identify the noises as the outliers of training…

Computer Vision and Pattern Recognition · Computer Science 2025-10-16 Xuanyu Yi , Kaihua Tang , Xian-Sheng Hua , Joo-Hwee Lim , Hanwang Zhang

Understanding the generalization properties of optimization algorithms under heavy-tailed noise has gained growing attention. However, the existing theoretical results mainly focus on stochastic gradient descent (SGD) and the analysis of…

We study a scalable alternative to robust gradient descent (RGD) techniques that can be used when the gradients can be heavy-tailed, though this will be unknown to the learner. The core technique is simple: instead of trying to robustly…

Machine Learning · Statistics 2020-12-16 Matthew J. Holland

Optimization plays a key role in machine learning. Recently, stochastic second-order methods have attracted much attention due to their low computational cost in each iteration. However, these algorithms might perform poorly especially if…

Machine Learning · Computer Science 2017-10-25 Haishan Ye , Zhihua Zhang

Deep neural policies have unlocked agile flight for quadcopters, adaptive grasping for manipulators, and reliable navigation for ground robots, yet their millions of weights conflict with the tight memory and real-time constraints of…

Robotics · Computer Science 2025-07-08 Maksym Shamrai

In this paper, we develop connections between two seemingly disparate, but central, models in robust statistics: Huber's epsilon-contamination model and the heavy-tailed noise model. We provide conditions under which this connection…

Machine Learning · Statistics 2019-07-03 Adarsh Prasad , Sivaraman Balakrishnan , Pradeep Ravikumar

With the rapid development of distributed optimization (DO) theory, the distributed stochastic gradient methods (DSGMs) occupy an important position. Although the theory of different DSGMs has been widely established, the main-stream…

Optimization and Control · Mathematics 2026-04-24 Zhan Yu , Zhongjie Shi , Deming Yuan

We study fundamental limits of first-order stochastic optimization in a range of nonconvex settings, including L-smooth functions satisfying Quasar-Convexity (QC), Quadratic Growth (QG), and Restricted Secant Inequalities (RSI). While the…

Machine Learning · Statistics 2025-06-03 El Mehdi Saad , Wei-Cheng Lee , Francesco Orabona

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

We develop an exact coordinate descent algorithm for high-dimensional regularized Huber regression. In contrast to composite gradient descent methods, our algorithm fully exploits the advantages of coordinate descent when the underlying…

Methodology · Statistics 2025-10-16 Younghoon Kim , Po-Ling Loh , Sumanta Basu

Numerous empirical evidence has corroborated that the noise plays a crucial rule in effective and efficient training of neural networks. The theory behind, however, is still largely unknown. This paper studies this fundamental problem…

Machine Learning · Computer Science 2019-09-10 Mo Zhou , Tianyi Liu , Yan Li , Dachao Lin , Enlu Zhou , Tuo Zhao

In this paper, we characterize the noise of stochastic gradients and analyze the noise-induced dynamics during training deep neural networks by gradient-based optimizers. Specifically, we firstly show that the stochastic gradient noise…

Machine Learning · Computer Science 2021-09-22 Yixin Wu , Rui Luo , Chen Zhang , Jun Wang , Yaodong Yang

Using tail bounds, we introduce a new probabilistic condition for function estimation in stochastic derivative-free optimization which leads to a reduction in the number of samples and eases algorithmic analyses. Moreover, we develop simple…

Optimization and Control · Mathematics 2023-06-16 Francesco Rinaldi , Luis Nunes Vicente , Damiano Zeffiro

This paper presents a general approach to linear stochastic processes driven by various random noises. Mathematically, such processes are described by linear stochastic differential equations of arbitrary order (the simplest non-trivial…

Condensed Matter · Physics 2009-10-28 Alon Drory

Stochastic gradient optimization is the dominant learning paradigm for a variety of scenarios, from classical supervised learning to modern self-supervised learning. We consider stochastic gradient algorithms for learning problems whose…

Machine Learning · Statistics 2025-08-29 Facheng Yu , Ronak Mehta , Alex Luedtke , Zaid Harchaoui

Due to the effectiveness of second-order algorithms in solving classical optimization problems, designing second-order optimizers to train deep neural networks (DNNs) has attracted much research interest in recent years. However, because of…

Machine Learning · Computer Science 2024-03-06 Ying Sun , Hongwei Yong , Lei Zhang

We propose a new Bayesian strategy for adaptation to smoothness in nonparametric models based on heavy tailed series priors. We illustrate it in a variety of settings, showing in particular that the corresponding Bayesian posterior…

Statistics Theory · Mathematics 2024-05-30 Sergios Agapiou , Ismaël Castillo

We provide a novel computer-assisted technique for systematically analyzing first-order methods for optimization. In contrast with previous works, the approach is particularly suited for handling sublinear convergence rates and stochastic…

Optimization and Control · Mathematics 2021-12-22 Adrien Taylor , Francis Bach

We study stochastic convex optimization with heavy-tailed data under the constraint of differential privacy (DP). Most prior work on this problem is restricted to the case where the loss function is Lipschitz. Instead, as introduced by…

Machine Learning · Computer Science 2022-11-02 Gautam Kamath , Xingtu Liu , Huanyu Zhang
‹ Prev 1 8 9 10 Next ›