English
Related papers

Related papers: Generalized Optimization: A First Step Towards Cat…

200 papers

This work aims to provide understandings on the remarkable success of deep convolutional neural networks (CNNs) by theoretically analyzing their generalization performance and establishing optimization guarantees for gradient descent based…

Machine Learning · Computer Science 2018-05-29 Pan Zhou , Jiashi Feng

In this paper, we present new second-order algorithms for composite convex optimization, called Contracting-domain Newton methods. These algorithms are affine-invariant and based on global second-order lower approximation for the smooth…

Optimization and Control · Mathematics 2020-12-23 Nikita Doikov , Yurii Nesterov

This paper is devoted to the study of stochastic optimization problems under the generalized smoothness assumption. By considering the unbiased gradient oracle in Stochastic Gradient Descent, we provide strategies to achieve in bounds the…

Optimization and Control · Mathematics 2025-05-26 Aleksandr Lobanov , Alexander Gasnikov

This paper shows that a wide class of effective learning rules -- those that improve a scalar performance measure over a given time window -- can be rewritten as natural gradient descent with respect to a suitably defined loss function and…

Machine Learning · Computer Science 2024-09-26 Lucas Shoji , Kenta Suzuki , Leo Kozachkov

The generalization error curve of certain kernel regression method aims at determining the exact order of generalization error with various source condition, noise level and choice of the regularization parameter rather than the minimax…

Machine Learning · Computer Science 2024-11-26 Yicheng Li , Weiye Gan , Zuoqiang Shi , Qian Lin

This article presents a generic approach to convolution that significantly differs from conventional methodologies in the current Machine Learning literature. The approach, in its mathematical aspects, proved to be clear and concise,…

Machine Learning · Computer Science 2025-08-29 Roberto Dias Algarte

Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specialization, and Bayesian uncertainty tracking. These phenomena appear across architectures -- in…

Machine Learning · Computer Science 2026-01-01 Alan Oursland

Reverse-mode differentiation is used for optimization, but it introduces references, which break the purity of the underlying programs, making them notoriously harder to optimize. We present a reverse-mode differentiation on a purely…

Programming Languages · Computer Science 2023-04-27 Mathieu Huot , Amir Shaikhha

We consider distributed optimization problems where networked nodes cooperatively minimize the sum of their locally known convex costs. A popular class of methods to solve these problems are the distributed gradient methods, which are…

Information Theory · Computer Science 2017-02-21 Dragana Bajovic , Dusan Jakovetic , Natasa Krejic , Natasa Krklec Jerinkic

Efforts to understand the generalization mystery in deep learning have led to the belief that gradient-based optimization induces a form of implicit regularization, a bias towards models of low "complexity." We study the implicit…

Machine Learning · Computer Science 2019-10-29 Sanjeev Arora , Nadav Cohen , Wei Hu , Yuping Luo

Adaptive gradient methods, which adopt historical gradient information to automatically adjust the learning rate, despite the nice property of fast convergence, have been observed to generalize worse than stochastic gradient descent (SGD)…

Machine Learning · Computer Science 2020-06-24 Jinghui Chen , Dongruo Zhou , Yiqi Tang , Ziyan Yang , Yuan Cao , Quanquan Gu

Regularizing the gradient norm of the output of a neural network with respect to its inputs is a powerful technique, rediscovered several times. This paper presents evidence that gradient regularization can consistently improve…

Machine Learning · Computer Science 2018-05-28 Dániel Varga , Adrián Csiszárik , Zsolt Zombori

Motivated by machine learning problems over large data sets and distributed optimization over networks, we develop and analyze a new method called incremental Newton method for minimizing the sum of a large number of strongly convex…

Optimization and Control · Mathematics 2016-04-05 Mert Gürbüzbalaban , Asuman Ozdaglar , Pablo Parrilo

We investigate the generalization and optimization properties of shallow neural-network classifiers trained by gradient descent in the interpolating regime. Specifically, in a realizable scenario where model weights can achieve arbitrarily…

Machine Learning · Statistics 2023-03-29 Hossein Taheri , Christos Thrampoulidis

The paper considers the problem of network-based computation of global minima in smooth nonconvex optimization problems. It is known that distributed gradient-descent-type algorithms can achieve convergence to the set of global minima by…

Optimization and Control · Mathematics 2019-10-24 Brian Swenson , Anirudh Sridhar , H. Vincent Poor

Many supervised learning tasks have intrinsic symmetries, such as translational and rotational symmetry in image classifications. These symmetries can be exploited to enhance performance. We formulate the symmetry constraints into a concise…

Quantum Physics · Physics 2024-08-14 Kaiming Bian , Shitao Zhang , Fei Meng , Wen Zhang , Oscar Dahlsten

Many modern machine learning applications, such as multi-task learning, require finding optimal model parameters to trade-off multiple objective functions that may conflict with each other. The notion of the Pareto set allows us to focus on…

Optimization and Control · Mathematics 2022-09-05 Mao Ye , Qiang Liu

Gradient descent method, as one of the major methods in numerical optimization, is the key ingredient in many machine learning algorithms. As one of the most fundamental way to solve the optimization problems, it promises the function value…

Quantum Physics · Physics 2021-02-01 Keren Li , Shijie Wei , Feihao Zhang , Pan Gao , Zengrong Zhou , Tao Xin , Xiaoting Wang , Guilu Long

For strongly convex objectives that are smooth, the classical theory of gradient descent ensures linear convergence relative to the number of gradient evaluations. An analogous nonsmooth theory is challenging. Even when the objective is…

Optimization and Control · Mathematics 2023-01-19 X. Y. Han , Adrian S. Lewis

Decentralized learning offers privacy and communication efficiency when data are naturally distributed among agents communicating over an underlying graph. Motivated by overparameterized learning settings, in which models are trained to…

Machine Learning · Computer Science 2023-03-28 Hossein Taheri , Christos Thrampoulidis