Offline reinforcement learning with realizability and single-policy concentrability
Sample-efficiency guarantees for offline reinforcement learning (RL) often rely on strong
assumptions on both the function classes (eg, Bellman-completeness) and the data …
assumptions on both the function classes (eg, Bellman-completeness) and the data …
The complexity of constrained min-max optimization
Despite its important applications in Machine Learning, min-max optimization of objective
functions that are nonconvex-nonconcave remains elusive. Not only are there no known first …
functions that are nonconvex-nonconcave remains elusive. Not only are there no known first …
Distributionally robust federated averaging
In this paper, we study communication efficient distributed algorithms for distributionally
robust federated learning via periodic averaging with adaptive sampling. In contrast to …
robust federated learning via periodic averaging with adaptive sampling. In contrast to …
Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with O (1/k^ 2) Rate on Squared Gradient Norm
In this work, we study the computational complexity of reducing the squared gradient
magnitude for smooth minimax optimization problems. First, we present algorithms with …
magnitude for smooth minimax optimization problems. First, we present algorithms with …
Efficient methods for structured nonconvex-nonconcave min-max optimization
The use of min-max optimization in the adversarial training of deep neural network
classifiers, and the training of generative adversarial networks has motivated the study of …
classifiers, and the training of generative adversarial networks has motivated the study of …
Sublinear convergence rates of extragradient-type methods: A survey on classical and recent developments
Q Tran-Dinh - arxiv preprint arxiv:2303.17192, 2023 - arxiv.org
The extragradient (EG), introduced by GM Korpelevich in 1976, is a well-known method to
approximate solutions of saddle-point problems and their extensions such as variational …
approximate solutions of saddle-point problems and their extensions such as variational …
Global convergence and variance reduction for a class of nonconvex-nonconcave minimax problems
Nonconvex minimax problems appear frequently in emerging machine learning
applications, such as generative adversarial networks and adversarial learning. Simple …
applications, such as generative adversarial networks and adversarial learning. Simple …
A single-loop smoothed gradient descent-ascent algorithm for nonconvex-concave min-max problems
Nonconvex-concave min-max problem arises in many machine learning applications
including minimizing a pointwise maximum of a set of nonconvex functions and robust …
including minimizing a pointwise maximum of a set of nonconvex functions and robust …
Faster single-loop algorithms for minimax optimization without strong concavity
Gradient descent ascent (GDA), the simplest single-loop algorithm for nonconvex minimax
optimization, is widely used in practical applications such as generative adversarial …
optimization, is widely used in practical applications such as generative adversarial …
Federated minimax optimization: Improved convergence analyses and algorithms
In this paper, we consider nonconvex minimax optimization, which is gaining prominence in
many modern machine learning applications, such as GANs. Large-scale edge-based …
many modern machine learning applications, such as GANs. Large-scale edge-based …