English
Related papers

Related papers: On the Impossibility of Global Convergence in Mult…

200 papers

Policy gradient (PG) methods have played an essential role in the empirical successes of reinforcement learning. In order to handle large state-action spaces, PG methods are typically used with function approximation. In this setting, the…

Deep learning is built on the foundational guarantee that gradient descent on an objective function converges to local minima. Unfortunately, this guarantee fails in settings, such as generative adversarial nets, that exhibit multiple…

Machine Learning · Computer Science 2019-05-14 Alistair Letcher , David Balduzzi , Sebastien Racaniere , James Martens , Jakob Foerster , Karl Tuyls , Thore Graepel

The study of convex optimization has historically been concerned with worst-case convergence rates. The development of the Optimized Gradient Method (OGM), due to \citet{drori2012PerformanceOF,Kim2016optimal}, marked a major milestone in…

Optimization and Control · Mathematics 2026-04-21 Benjamin Grimmer , Kevin Shu , Alex L. Wang

The behaviour of multi-agent learning in competitive settings is often considered under the restrictive assumption of a zero-sum game. Only under this strict requirement is the behaviour of learning well understood; beyond this, learning…

Computer Science and Game Theory · Computer Science 2023-07-27 Aamal Hussain , Francesco Belardinelli , Georgios Piliouras

Gradient-variation online learning aims to achieve regret guarantees that scale with variations in the gradients of online functions, which has been shown to be crucial for attaining fast convergence in games and robustness in stochastic…

Machine Learning · Computer Science 2024-11-05 Yan-Feng Xie , Peng Zhao , Zhi-Hua Zhou

With the success of modern machine learning, it is becoming increasingly important to understand and control how learning algorithms interact. Unfortunately, negative results from game theory show there is little hope of understanding or…

In this work, we establish near-linear and strong convergence for a natural first-order iterative algorithm that simulates Von Neumann's Alternating Projections method in zero-sum games. First, we provide a precise analysis of Optimistic…

Optimization and Control · Mathematics 2021-08-18 Ioannis Anagnostides , Paolo Penna

Gradient descent finds a global minimum in training deep neural networks despite the objective function being non-convex. The current paper proves gradient descent achieves zero training loss in polynomial time for a deep over-parameterized…

Machine Learning · Computer Science 2019-05-30 Simon S. Du , Jason D. Lee , Haochuan Li , Liwei Wang , Xiyu Zhai

Model-based reinforcement learning (MBRL) agents typically learn world models by minimizing predictive loss. However, powerful RL optimizers inevitably exploit minor model inaccuracies, leading to simulator exploitation and a reality gap…

Machine Learning · Computer Science 2026-05-29 Christoph Dann , Yishay Mansour , Mehryar Mohri

Many machine learning and data science tasks require solving non-convex optimization problems. When the loss function is a sum of multiple terms, a popular method is the stochastic gradient descent. Viewed as a process for sampling the loss…

Machine Learning · Computer Science 2021-09-10 Jing An , Lexing Ying

Consider a strongly monotone game where the players' utility functions include a reward function and a linear term for each dimension, with coefficients that are controlled by the manager. Gradient play converges to a unique Nash…

Multiagent Systems · Computer Science 2026-02-25 Siddharth Chandak , Ilai Bistritz , Nicholas Bambos

Meta learning with multiple objectives can be formulated as a Multi-Objective Bi-Level optimization Problem (MOBLP) where the upper-level subproblem is to solve several possible conflicting targets for the meta learner. However, existing…

Machine Learning · Computer Science 2021-02-16 Feiyang Ye , Baijiong Lin , Zhixiong Yue , Pengxin Guo , Qiao Xiao , Yu Zhang

Learning Gaussian Mixture Models (GMMs) is a fundamental problem in machine learning, with the Expectation-Maximization (EM) algorithm and its popular variant gradient EM being arguably the most widely used algorithms in practice. In the…

Machine Learning · Computer Science 2025-06-10 Mo Zhou , Weihang Xu , Maryam Fazel , Simon S. Du

In this work, we study the problem of finding Pareto optimal policies in multi-agent reinforcement learning problems with cooperative reward structures. We show that any algorithm where each agent only optimizes their reward is subject to…

Machine Learning · Computer Science 2024-10-28 Bang Giang Le , Viet Cuong Ta

Despite the success of generative adversarial networks (GANs) in generating visually appealing images, they are notoriously challenging to train. In order to stabilize the learning dynamics in minimax games, we propose a novel recursive…

Machine Learning · Computer Science 2022-11-01 Zichu Liu , Lacra Pavel

We consider the gradient method with variable step size for minimizing functions that are definable in o-minimal structures on the real field and differentiable with locally Lipschitz gradients. We prove that global convergence holds if…

Optimization and Control · Mathematics 2024-12-02 Cédric Josz

Adversarial training, a special case of multi-objective optimization, is an increasingly prevalent machine learning technique: some of its most notable applications include GAN-based generative modeling and self-play techniques in…

Machine Learning · Statistics 2021-03-17 Gauthier Gidel , David Balduzzi , Wojciech Marian Czarnecki , Marta Garnelo , Yoram Bachrach

In distributed optimization problems, a technique called gradient coding, which involves replicating data points, has been used to mitigate the effect of straggling machines. Recent work has studied approximate gradient coding, which…

Machine Learning · Statistics 2021-08-09 Margalit Glasgow , Mary Wootters

We propose a new gradient descent algorithm with added stochastic terms for finding the global optimizers of nonconvex optimization problems. A key component in the algorithm is the adaptive tuning of the randomness based on the value of…

Optimization and Control · Mathematics 2025-06-16 Björn Engquist , Kui Ren , Yunan Yang

In machine learning, stochastic gradient descent (SGD) is widely deployed to train models using highly non-convex objectives with equally complex noise models. Unfortunately, SGD theory often makes restrictive assumptions that fail to…

Machine Learning · Computer Science 2022-10-11 Vivak Patel , Shushu Zhang , Bowen Tian