# From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications

arXiv: https://arxiv.org/abs/2506.03464 · HTML: https://mlsanity.com/paper/2506.03464/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 73 references that are in the map.
- First posted on arXiv 4 Jun 2025.

## Builds on (most cited first, 30 of 48)

- [Self-Play Preference Optimization for Language Model Alignment](https://mlsanity.com/paper/2405.00675/) (2024)
- [Nash Learning from Human Feedback](https://mlsanity.com/paper/2312.00886/) (2023)
- [Training GANs with Optimism](https://mlsanity.com/paper/1711.00141/) (2017)
- [Optimization, Learning, and Games with Predictable Sequences](https://mlsanity.com/paper/1311.1869/) (2013)
- [Fast Convergence of Regularized Learning in Games](https://mlsanity.com/paper/1507.00407/) (2015)
- [A Minimaximalist Approach to Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2401.04056/) (2024)
- [Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning](https://mlsanity.com/paper/2206.15378/) (2022)
- [Cycles in adversarial regularized learning](https://mlsanity.com/paper/1709.02738/) (2017)
- [The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimization](https://mlsanity.com/paper/1807.03907/) (2018)
- [Last-Iterate Convergence: Zero-Sum Games and Constrained Min-Max Optimization](https://mlsanity.com/paper/1807.04252/) (2018)
- [Near-Optimal No-Regret Learning in General Games](https://mlsanity.com/paper/2108.06924/) (2021)
- [Solving Large Imperfect Information Games Using CFR+](https://mlsanity.com/paper/1407.5042/) (2014)
- [Lower complexity bounds of first-order methods for convex-concave bilinear saddle-point problems](https://mlsanity.com/paper/1808.02901/) (2018)
- [Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with O(1/k2) Rate on Squared Gradient Norm](https://mlsanity.com/paper/2102.07922/) (2021)
- [Fast Policy Extragradient Methods for Competitive Games with Entropy Regularization](https://mlsanity.com/paper/2105.15186/) (2021)
- [Halpern Iteration for Near-Optimal and Parameter-Free Monotone Inclusion and Strong Solutions to Variational Inequalities](https://mlsanity.com/paper/2002.08872/) (2020)
- [Last Iterate is Slower than Averaged Iterate in Smooth Convex-Concave Saddle Point Problems](https://mlsanity.com/paper/2002.00057/) (2020)
- [Hedging in games: Faster convergence of external and swap regrets](https://mlsanity.com/paper/2006.04953/) (2020)
- [Adaptive Learning in Continuous Games: Optimal Regret Bounds and Convergence to Nash Equilibrium](https://mlsanity.com/paper/2104.12761/) (2021)
- [Tight last-iterate convergence rates for no-regret learning in multi-player games](https://mlsanity.com/paper/2010.13724/) (2020)
- [Near-Optimal No-Regret Learning for Correlated Equilibria in Multi-Player General-Sum Games](https://mlsanity.com/paper/2111.06008/) (2021)
- [Uncoupled Learning Dynamics with O(log T) Swap Regret in Multiplayer Games](https://mlsanity.com/paper/2204.11417/) (2022)
- [Last-Iterate Convergence of Optimistic Gradient Method for Monotone Variational Inequalities](https://mlsanity.com/paper/2205.08446/) (2022)
- [Accelerated Single-Call Methods for Constrained Min-Max Optimization](https://mlsanity.com/paper/2210.03096/) (2022)
- [Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games with Bandit Feedback](https://mlsanity.com/paper/2303.02738/) (2023)
- [Statistical Impossibility and Possibility of Aligning LLMs with Human Preferences: From Condorcet Paradox to Nash Equilibrium](https://mlsanity.com/paper/2503.10990/) (2025)
- [Independent Learning in Stochastic Games](https://mlsanity.com/paper/2111.11743/) (2021)
- [The Power of Regularization in Solving Extensive-Form Games](https://mlsanity.com/paper/2206.09495/) (2022)
- [Accelerated Algorithms for Constrained Nonconvex-Nonconcave Min-Max Optimization and Comonotone Inclusion](https://mlsanity.com/paper/2206.05248/) (2022)
- [Regularized Gradient Descent Ascent for Two-Player Zero-Sum Markov Games](https://mlsanity.com/paper/2205.13746/) (2022)

## Built on by (most cited first, 8 of 8)

- [Efficient Uncoupled Learning Dynamics with tildeO!left(T-1/4right) Last-Iterate Convergence in Bilinear Saddle-Point Problems over Convex Sets under Bandit Feedback](https://mlsanity.com/paper/2602.21436/) (2026)
- [Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions](https://mlsanity.com/paper/2605.09363/) (2026)
- [Tight Regret Upper and Lower Bounds for Optimistic Hedge in Two-Player Zero-Sum Games](https://mlsanity.com/paper/2510.11691/) (2025)
- [Last-Iterate Analyses of FTRL with the 1/2-Tsallis Entropy in Stochastic Bandits](https://mlsanity.com/paper/2510.22819/) (2025)
- [Minimax Last-Iterate Convergence in Matrix Games with Observed Actions](https://mlsanity.com/paper/2609.34656/) (2026)
- [Polylogarithmic Nash Regret in Matrix Games with Bandit Feedback](https://mlsanity.com/paper/2609.34812/) (2026)
- [Fast Last-Iterate Convergence in Zero-Sum Markov Games with Bandit Feedback](https://mlsanity.com/paper/2610.05968/) (2026)
- [IR-PRM+ with Previous-Utility Prediction: Constant Regret and Best-Iterate Convergence](https://mlsanity.com/paper/2610.19016/) (2026)

## Abstract (arXiv)

The convergence of online learning algorithms in games under self-play is a fundamental question in game theory and machine learning. Among various notions of convergence, last-iterate convergence is particularly desirable, as it reflects the actual decisions made by the learners and captures the day-to-day behavior of the learning dynamics. While many algorithms are known to converge in the average-iterate, achieving last-iterate convergence typically requires considerably more effort in both the design and the analysis of the algorithm. Somewhat surprisingly, we show in this paper that for a large family of games, there exists a simple black-box reduction that transforms the average iterates of an uncoupled learning dynamics into the last iterates of a new uncoupled learning dynamics, thus also providing a reduction from last-iterate convergence to average-iterate convergence. Our reduction applies to games where each player's utility is linear in both their own strategy and the joint strategy of all opponents. This family includes two-player bimatrix games and generalizations such as multi-player polymatrix games. By applying our reduction to the Optimistic Multiplicative Weights Update algorithm, we obtain new state-of-the-art last-iterate convergence rates for uncoupled learning dynamics in multi-player zero-sum polymatrix games: (1) an O(fraclog dT) last-iterate convergence rate under gradient feedback, representing an exponential improvement in the dependence on the dimension d (i.e., the maximum number of actions available to either player); and (2) an widetildeO(d^frac15 T^-frac15) last-iterate convergence rate under bandit feedback, improving upon the previous best rates of widetildeO(√d T^-frac18) and widetildeO(√d T^-frac16).