No article text was recorded for this version.
asymmetric learning rates (two-timescale gradient descent ascent)
Version 1 of 133 papers42 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Independent Policy Gradient Methods for Competitive Reinforcement Learning
- Blog: On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems
- Blog: Diffusion Stochastic Optimization for Min-Max Problems
- Blog: Global Convergence to Local Minmax Equilibrium in Classes of Nonconvex Zero-Sum Games
- Blog: TiAda: A Time-scale Adaptive Algorithm for Nonconvex Minimax Optimization
- Blog: SGDA with shuffling: faster convergence for nonconvex-PŁ minimax optimization
- Blog: Convergence Rates of Two-Time-Scale Gradient Descent-Ascent Dynamics for Solving Nonconvex Min-Max Problems
- Blog: Achieving Near-Optimal Convergence for Distributed Minimax Optimization with Adaptive Stepsizes
- Blog: Open problem: Convergence of single-timescale mean-field Langevin descent-ascent for two-player zero-sum games
- Blog: Self-Attention Generative Adversarial Networks
- Blog: AdaGDA: Faster Adaptive Gradient Descent Ascent Methods for Minimax Optimization
- Blog: Finite-sample Analysis of Greedy-GQ with Linear Function Approximation under Markovian Noise
- Blog: Existence and Estimation of Critical Batch Size for Training Generative Adversarial Networks with Two Time-Scale Update Rule
- Blog: Double-Step Alternating Extragradient with Increasing Timescale Separation for Finding Local Minimax Points: Provable Improvements
- Blog: A Survey on Generative Adversarial Networks: Variants, Applications, and Training
- Blog: Improved Rates of Differentially Private Nonconvex-Strongly-Concave Minimax Optimization
- Blog: Train simultaneously, generalize better: Stability of gradient-based minimax learners
- Blog: Communication-Efficient Distributionally Robust Decentralized Learning
- Blog: Explore Aggressively, Update Conservatively: Stochastic Extragradient Methods with Variable Stepsize Scaling
- Blog: Local Convergence Analysis of Gradient Descent Ascent with Finite Timescale Separation
- Blog: Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential Game
- Blog: What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization?
- Blog: Convergence of Mean-Field Langevin Stochastic Descent-Ascent for Distributional Minimax Optimization
- Blog: Online Min-max Problems with Non-convexity and Non-stationarity
- Blog: Generative Adversarial Networks (GANs): Challenges, Solutions, and Future Directions
- Blog: Implicit Learning Dynamics in Stackelberg Games: Equilibria Characterization, Convergence Analysis, and Empirical Study
- Blog: SAGDA: Achieving $\mathcal{O}(\epsilon^{-2})$ Communication Complexity in Federated Min-Max Learning
- Blog: On-Demand Sampling: Learning Optimally from Multiple Distributions
- Blog: Solving Non-Convex Non-Differentiable Min-Max Games using Proximal Gradient Method
- Blog: Two-Scale Gradient Descent Ascent Dynamics Finds Mixed Nash Equilibria of Continuous Games: A Mean-Field Perspective
- Blog: Convergence of Mean-Field Langevin Stochastic Descent-Ascent for Distributional Minimax Optimization
- Blog: On the One-sided Convergence of Adam-type Algorithms in Non-convex Non-concave Min-max Optimization
- Blog: Open Problem: Is There a First-Order Method that Only Converges to Local Minimax Optima?
History & citation
Current · Permanent link
- This direction split from Two-Timescale Gradient Descent Ascent for Minimax Optimization (52% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_asymmetric_learning_rates_two_timescale__8ab20017,
title = {asymmetric learning rates (two-timescale gradient descent ascent)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/asymmetric-learning-rates-two-timescale-gradient-descent-ascent/rdr_8ab2001711114a2bb55890985753c10d},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_asymmetric_learning_rates_two_timescale__8ab20017_v1,
title = {asymmetric learning rates (two-timescale gradient descent ascent)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/asymmetric-learning-rates-two-timescale-gradient-descent-ascent/rdr_8ab2001711114a2bb55890985753c10d/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}