English
Related papers

Related papers: Approximate Last Iterate Convergence in Overparame…

200 papers

The choice of parameters, and the design of the network architecture are important factors affecting the performance of deep neural networks. Genetic Algorithms (GA) have been used before to determine parameters of a network. Yet, GAs…

Computer Vision and Pattern Recognition · Computer Science 2018-09-28 Yantao Lu , Burak Kakillioglu , Senem Velipasalar

The convergence of the Conjugate Gradient method is subject to a locality limitation which imposes a lower bound on the number of iterations required before a qualitatively accurate approximation can be obtained. This limitation originates…

Numerical Analysis · Mathematics 2026-01-16 Ulrich Rüde

Modern machine learning paradigms, such as deep learning, occur in or close to the interpolation regime, wherein the number of model parameters is much larger than the number of data samples. In this work, we propose a regularity condition…

Machine Learning · Computer Science 2023-06-06 Chaoyue Liu , Dmitriy Drusvyatskiy , Mikhail Belkin , Damek Davis , Yi-An Ma

We study in this paper the rate of convergence for learning densities under the Generative Adversarial Networks (GAN) framework, borrowing insights from nonparametric statistics. We introduce an improved GAN estimator that achieves a faster…

Machine Learning · Statistics 2018-02-20 Tengyuan Liang

We study the convergence rate of Bregman gradient methods for convex optimization in the space of measures on a $d$-dimensional manifold. Under basic regularity assumptions, we show that the suboptimality gap at iteration $k$ is in…

Optimization and Control · Mathematics 2023-03-15 Lénaïc Chizat

Deep learning approaches deliver state-of-the-art performance in recognition of spatiotemporal human motion data. However, one of the main challenges in these recognition tasks is limited available training data. Insufficient training data…

Computer Vision and Pattern Recognition · Computer Science 2023-08-14 Junxiao Shen , John Dudley , Per Ola Kristensson

In this paper, we demonstrate, both theoretically and by numerical examples, that adding a local prediction component to the update rule can significantly improve the convergence rate of distributed averaging algorithms. We focus on the…

Distributed, Parallel, and Cluster Computing · Computer Science 2015-05-13 Boris N. Oreshkin , Mark J. Coates , Michael G. Rabbat

We present a continual learning approach for generative adversarial networks (GANs), by designing and leveraging parameter-efficient feature map transformations. Our approach is based on learning a set of global and task-specific…

Machine Learning · Computer Science 2021-08-02 Sakshi Varshney , Vinay Kumar Verma , Srijith P K , Lawrence Carin , Piyush Rai

It is well understood that neural networks with carefully hand-picked weights provide powerful function approximation and that they can be successfully trained in over-parametrized regimes. Since over-parametrization ensures zero training…

Machine Learning · Computer Science 2024-05-21 G. Welper

Training generative adversarial networks requires balancing of delicate adversarial dynamics. Even with careful tuning, training may diverge or end up in a bad equilibrium with dropped modes. In this work, we improve CS-GAN with natural…

Machine Learning · Computer Science 2020-07-02 Yan Wu , Jeff Donahue , David Balduzzi , Karen Simonyan , Timothy Lillicrap

Modern machine learning models are often trained in a setting where the number of parameters exceeds the number of training samples. To understand the implicit bias of gradient descent in such overparameterized models, prior work has…

Machine Learning · Statistics 2025-10-29 Hannes Matt , Dominik Stöger

Generative adversarial networks (GANs) have been extremely effective in approximating complex distributions of high-dimensional, input data samples, and substantial progress has been made in understanding and improving GAN performance in…

Machine Learning · Computer Science 2018-05-01 Daniel Jiwoong Im , He Ma , Graham Taylor , Kristin Branson

We study how well generative adversarial networks (GAN) learn probability distributions from finite samples by analyzing the convergence rates of these models. Our analysis is based on a new oracle inequality that decomposes the estimation…

Machine Learning · Computer Science 2022-05-26 Yunfei Yang

The Past Extragradient (PEG) [Popov, 1980] method, also known as the Optimistic Gradient method, has known a recent gain in interest in the optimization community with the emergence of variational inequality formulations for machine…

Optimization and Control · Mathematics 2022-11-01 Eduard Gorbunov , Adrien Taylor , Gauthier Gidel

We study adversarial learning when the target distribution factorizes according to a known Bayesian network. For interpolative divergences, including $(f,\Gamma)$-divergences, we prove a new infimal subadditivity principle showing that,…

Machine Learning · Statistics 2026-04-03 Panagiota Birmpa , Eric Joseph Hall

We study the last-iterate convergence of variance reduction methods for extragradient (EG) algorithms for a class of variational inequalities satisfying error-bound conditions. Previously, last-iterate linear convergence was only known…

Optimization and Control · Mathematics 2024-01-02 Tianlong Nan , Yuan Gao , Christian Kroer

Fitting neural networks often resorts to stochastic (or similar) gradient descent which is a noise-tolerant (and efficient) resolution of a gradient descent dynamics. It outputs a sequence of networks parameters, which sequence evolves…

Machine Learning · Statistics 2021-04-15 Gabriel Turinici

This paper introduces a general framework for iterative optimization algorithms and establishes under general assumptions that their convergence is asymptotically geometric. We also prove that under appropriate assumptions, the rate of…

Machine Learning · Statistics 2023-02-27 Randal Douc , Sylvain Le Corff

We present a new approach to using neural networks to approximate the solutions of variational equations, based on the adaptive construction of a sequence of finite-dimensional subspaces whose basis functions are realizations of a sequence…

Machine Learning · Computer Science 2021-06-01 Mark Ainsworth , Justin Dong

Invoking the manifold assumption in machine learning requires knowledge of the manifold's geometry and dimension, and theory dictates how many samples are required. However, in applications data are limited, sampling may not be uniform, and…

Machine Learning · Computer Science 2023-03-02 Luciano Dyballa , Steven W. Zucker