No article text was recorded for this version.
last-iterate convergence (last-iterate convergence guarantee)
Version 1 of 172 papers95 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Non-Ergodic Alternating Proximal Augmented Lagrangian Algorithms with Optimal Rates
- Blog: Adaptive Extra-Gradient Methods for Min-Max Optimization and Games
- Blog: Demystifying the Myths and Legends of Nonconvex Convergence of SGD
- Blog: A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees
- Blog: Provable Last-Iterate Convergence for Multi-Objective Safe LLM Alignment via Optimistic Primal-Dual
- Blog: A Primal-Dual Algorithmic Framework for Constrained Convex Minimization
- Blog: ANITA: An Optimal Loopless Accelerated Variance-Reduced Gradient Method
- Blog: On Almost Sure Convergence Rates of Stochastic Gradient Methods
- Blog: Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with O(1/k^2) Rate on Squared Gradient Norm
- Blog: A Comprehensive Framework for Analyzing the Convergence of Adam: Bridging the Gap with SGD
- Blog: On the Convergence of AdaGrad on $\R^{d}$: Beyond Convexity, Non-Asymptotic Rate and Acceleration
- Blog: On the Convergence of AdaGrad(Norm) on $\mathbb{R}^d$: Beyond Convexity, Non-Asymptotic Rate and Acceleration
- Blog: On the Convergence of AdaGrad(Norm) on ℝd: Beyond Convexity, Non-Asymptotic Rate and Acceleration
- Blog: Distributed Dual Subgradient Methods with Averaging and Applications to Grid Optimization
- Blog: Revisit last-iterate convergence of mSGD under milder requirement on step size
- Blog: On the Convergence of Mirror Descent beyond Stochastic Convex Programming
- Blog: Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with O(1/k^2) Rate on Squared Gradient Norm
- Blog: Stable Nonconvex-Nonconcave Training via Linear Interpolation
- Blog: SIFAR: A Simple Faster Accelerated Variance-Reduced Gradient Method
- Blog: Last-iterate convergence analysis of stochastic momentum methods for neural networks
- Blog: Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity and Last-Iterate Convergence
- Blog: Improved Last-Iterate Convergence of Shuffling Gradient Methods for Nonsmooth Convex Optimization
- Blog: Preconditioned primal-dual dynamics in convex optimization: non-ergodic convergence rates
- Blog: High Probability Convergence Bounds for Non-convex Stochastic Gradient Descent with Sub-Weibull Noise
- Blog: Almost Sure Last Iterate Convergence of Sharpness-Aware Minimization
- Blog: Benefits of Learning Rate Annealing for Tuning-Robustness in Stochastic Optimization
- Blog: Training GANs with Optimism
- Blog: Accelerated Single-Call Methods for Constrained Min-Max Optimization
- Blog: Last Iterate is Slower than Averaged Iterate in Smooth Convex-Concave Saddle Point Problems
- Blog: Safe Policy Iteration: A Monotonically Improving Approximate Policy Iteration Approach
- Blog: Reinforcement Learning for POMDPs Based on Action Values and Stochastic Optimization
- Blog: Fast and Strong Convergence of Online Learning Algorithms
- Blog: Accelerated Single-Call Methods for Constrained Min-Max Optimization
- Blog: Langevin Monte Carlo without smoothness
- Blog: Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm
- Blog: Independent Learning in Performative Markov Potential Games
- Blog: Random block coordinate methods for inconsistent convex optimisation problems
- Blog: On Markov Chain Gradient Descent
- Blog: Explore Aggressively, Update Conservatively: Stochastic Extragradient Methods with Variable Stepsize Scaling
- Blog: On Corruption-Robustness in Performative Reinforcement Learning
- Blog: On the Last-Iterate Convergence of Shuffling Gradient Methods
- Blog: Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity
- Blog: Online Min-max Problems with Non-convexity and Non-stationarity
- Blog: Last Iterate Convergence of Incremental Methods and Applications in Continual Learning
- Blog: Provably Efficient UCB-type Algorithms For Learning Predictive State Representations
- Blog: Event-Triggered Decentralized Federated Learning over Resource-Constrained Edge Devices
- Blog: When, Why and How Much? Adaptive Learning Rate Scheduling by Refinement
- Blog: On the Convergence of Single-Timescale Actor-Critic
- Blog: Closing the Gap: Achieving Global Convergence (Last Iterate) of Actor-Critic under Markovian Sampling with Neural Network Parametrization
- Blog: Distributed Proximal Splitting Algorithms with Rates and Acceleration
- Blog: Nesterov Accelerated Shuffling Gradient Method for Convex Optimization
- Blog: A unitary distributed subgradient method for multi-agent optimization with different coupling sources
- Blog: Stochastic Mirror Descent in Variationally Coherent Optimization Problems
- Blog: Last iterate convergence of SGD for Least-Squares in the Interpolation regime
- Blog: Unregularized Online Learning Algorithms with General Loss Functions
- Blog: Convergence of Unregularized Online Learning Algorithms
- Blog: Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs
- Blog: Closing the Gap: Achieving Global Convergence (Last Iterate) of Actor-Critic under Markovian Sampling with Neural Network Parametrization
- Blog: Stochastic Gradient Descent for Nonconvex Learning without Bounded Gradient Assumptions
- Blog: First-Order Algorithms for Min-Max Optimization in Geodesic Metric Spaces
Showing 60 of 72 papers.
History & citation
Current · Permanent link
- Last Iterate Convergence in Stochastic Optimization merged into this direction (61% overlap)
- This direction split from last-iterate convergence gap (54% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_last_iterate_convergence_last_iterate_co_fb25af49,
title = {last-iterate convergence (last-iterate convergence guarantee)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/last-iterate-convergence-last-iterate-convergence-guarantee/rdr_fb25af4981374d0d85832bb30c48b7cb},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_last_iterate_convergence_last_iterate_co_fb25af49_v1,
title = {last-iterate convergence (last-iterate convergence guarantee)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/last-iterate-convergence-last-iterate-convergence-guarantee/rdr_fb25af4981374d0d85832bb30c48b7cb/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}