English
Related papers

Related papers: Scale-Invariant Neural Network Optimization: Norm …

200 papers

In this paper, we prove new complexity bounds for zeroth-order methods in non-convex optimization with inexact observations of the objective function values. We use the Gaussian smoothing approach of Nesterov and Spokoiny [2015] and extend…

Optimization and Control · Mathematics 2021-01-14 Innokentiy Shibaev , Pavel Dvurechensky , Alexander Gasnikov

Understanding when the noise in stochastic gradient descent (SGD) affects generalization of deep neural networks remains a challenge, complicated by the fact that networks can operate in distinct training regimes. Here we study how the…

Machine Learning · Computer Science 2023-05-31 Antonio Sclocchi , Mario Geiger , Matthieu Wyart

Classical assumptions like strong convexity and Lipschitz smoothness often fail to capture the nature of deep learning optimization problems, which are typically non-convex and non-smooth, making traditional analyses less applicable. This…

Machine Learning · Computer Science 2025-05-01 Binchuan Qi , Wei Gong , Li Li

Neural scaling laws establish a predictable relationship between model performance and data or compute, offering crucial guidance for resource allocation in new domains and tasks. Yet such laws are most needed precisely where they are…

Machine Learning · Computer Science 2026-05-11 Xing Han , Ziyin Liu , Suchi Saria , Paul Pu Liang

Geometry-aware optimization algorithms, such as Muon, have achieved remarkable success in training deep neural networks (DNNs). These methods leverage the underlying geometry of DNNs by selecting appropriate norms for different layers and…

Machine Learning · Computer Science 2026-02-04 Jie Hao , Xiaochuan Gong , Jie Xu , Zhengdao Wang , Mingrui Liu

This work introduces a hybrid non-Euclidean optimization method which generalizes gradient norm clipping by combining steepest descent and conditional gradient approaches. The method achieves the best of both worlds by establishing a…

Machine Learning · Computer Science 2026-02-05 Thomas Pethick , Wanyun Xie , Mete Erdogan , Kimon Antonakopoulos , Antonio Silveti-Falls , Volkan Cevher

Scale is often seen as a given, disturbing factor in many vision tasks. When doing so it is one of the factors why we need more data during learning. In recent work scale equivariance was added to convolutional neural networks. It was shown…

Computer Vision and Pattern Recognition · Computer Science 2021-11-02 Ivan Sosnovik , Artem Moskalev , Arnold Smeulders

This paper considers optimization problems over networks where agents have individual objectives to meet, or individual parameter vectors to estimate, subject to subspace constraints that require the objectives across the network to lie in…

Multiagent Systems · Computer Science 2020-04-22 Roula Nassif , Stefan Vlaski , Ali H. Sayed

In this paper, we propose a generic and simple strategy for utilizing stochastic gradient information in optimization. The technique essentially contains two consecutive steps in each iteration: 1) computing and normalizing each block…

Machine Learning · Computer Science 2018-04-24 Adams Wei Yu , Lei Huang , Qihang Lin , Ruslan Salakhutdinov , Jaime Carbonell

We present two easy-to-implement gradient-free/zeroth-order methods to optimize a stochastic non-smooth function accessible only via a black-box. The methods are built upon efficient first-order methods in the heavy-tailed case, i.e., when…

Optimization and Control · Mathematics 2023-08-25 Nikita Kornilov , Alexander Gasnikov , Pavel Dvurechensky , Darina Dvinskikh

Achieving invariance to nuisance transformations is a fundamental challenge in the construction of robust and reliable vision systems. Existing approaches to invariance scale exponentially with the dimension of the family of…

Computer Vision and Pattern Recognition · Computer Science 2022-03-11 Sam Buchanan , Jingkai Yan , Ellie Haber , John Wright

An influential line of recent work has focused on the generalization properties of unregularized gradient-based learning procedures applied to separable linear classification with exponentially-tailed loss functions. The ability of such…

Machine Learning · Computer Science 2022-06-24 Matan Schliserman , Tomer Koren

Non-convex optimization problems are ubiquitous in machine learning, especially in Deep Learning. While such complex problems can often be successfully optimized in practice by using stochastic gradient descent (SGD), theoretical analysis…

Machine Learning · Computer Science 2022-02-21 Harsh Vardhan , Sebastian U. Stich

The development of nonlinear optimization algorithms capable of performing reliably in the presence of noise has garnered considerable attention lately. This paper advocates for strategies to create noise-tolerant nonlinear optimization…

Optimization and Control · Mathematics 2024-10-04 Yuchen Lou , Shigeng Sun , Jorge Nocedal

Inspired by two basic mechanisms in animal visual systems, we introduce a feature transform technique that imposes invariance properties in the training of deep neural networks. The resulting algorithm requires less parameter tuning, trains…

Computer Vision and Pattern Recognition · Computer Science 2021-12-10 Chengxi Ye , Xiong Zhou , Tristan McKinney , Yanfeng Liu , Qinggang Zhou , Fedor Zhdanov

While first-order optimization methods such as stochastic gradient descent (SGD) are popular in machine learning (ML), they come with well-known deficiencies, including relatively-slow convergence, sensitivity to the settings of…

Optimization and Control · Mathematics 2018-02-19 Peng Xu , Farbod Roosta-Khorasani , Michael W. Mahoney

Distributed optimization has become the default training paradigm in modern machine learning due to the growing scale of models and datasets. To mitigate communication overhead, local updates are often applied before global aggregation,…

Machine Learning · Computer Science 2025-08-15 Su Hyeong Lee , Manzil Zaheer , Tian Li

From the proliferative mechanisms generating neurons from progenitor cells to neuron migration and synaptic connection formation, several vicissitudes culminate in the mature brain. Both component loss and gain remain ubiquitous during…

Neurons and Cognition · Quantitative Biology 2024-08-06 Rodrigo Siqueira Kazu , Kleber Neves , Bruno Mota

Nowadays stochastic approximation methods are one of the major research direction to deal with the large-scale machine learning problems. From stochastic first order methods, now the focus is shifting to stochastic second order methods due…

Machine Learning · Computer Science 2019-12-30 Vinod Kumar Chauhan , Anuj Sharma , Kalpana Dahiya

We study the algorithmic problem of estimating the mean of heavy-tailed random vector in $\mathbb{R}^d$, given $n$ i.i.d. samples. The goal is to design an efficient estimator that attains the optimal sub-gaussian error bound, only assuming…

Statistics Theory · Mathematics 2020-02-19 Zhixian Lei , Kyle Luh , Prayaag Venkat , Fred Zhang