arXiv Machine Learning
Jun 2
Mirror Descent Under Generalized Smoothness
arXiv:2502. 00753v4 Announce Type: replace-cross Abstract: Smoothness is crucial for attaining fast rates in first-order optimization.
The Hidden Cost of Approximation in Online Mirror Descent
arXiv:2511. 22283v2 Announce Type: replace Abstract: Online mirror descent (OMD) is a fundamental algorithmic paradigm that underlies many algorithms in optimization, machine learning and sequential decision-making.
Related stories
arXiv Machine Learning
Sep 14
Block-Norm Geometries for Online Mirror Descent with Sparse Losses
The paper investigates how the choice of geometry in online mirror descent affects performance, particularly when loss gradients are sparse. It introduces randomized block‑norm mirror maps that interpolate between Euclidean and entropic geometries, achieving polynomial‑in‑dimension regret improvements over standard methods for various convex sets. The authors also demonstrate that naive alternation between mirror maps can lead to linear regret and propose a Hedge‑based meta‑algorithm that competes with the best mirror map in a finite portfolio, achieving near‑optimal regret for random block geometries.
arXiv Machine Learning
Oct 9
Composite Online-to-Nonconvex Conversion with Optimal Oracle Complexity
arXiv:2610. 12328v1 Announce Type: new Abstract: We consider stochastic nonsmooth nonconvex composite optimization, which includes several important problems such as constrained optimization and the regularized training of neural networks.
arXiv Machine Learning
Jun 11
Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization Sensitivity
arXiv:2606. 11431v1 Announce Type: new Abstract: Mirror Descent (MD) extends Gradient Descent (GD) beyond Euclidean geometry and has recently reappeared as a lens for KL-regularized policy optimization in reinforcement learning and LLM post-training.
arXiv Machine Learning
Jun 17
Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences
arXiv:2602. 23116v3 Announce Type: replace Abstract: We consider the problem of regularized best-response max-regret minimization in online RLHF under general preferences and bandit feedback.
arXiv Machine Learning
5d ago
Mirror descent algorithms with logarithmic barriers
arXiv:2608. 22834v2 Announce Type: replace-cross Abstract: We derive convergence guarantees for mirror descent and proximal mirror descent with a logarithmic barrier as the distance-generating function.
arXiv Machine Learning
Jun 19
Stabilizing Bandits using Regularization: Precise Regret and A Quantitative Central Limit Theorem
arXiv:2603. 10184v2 Announce Type: replace-cross Abstract: Statistical inference with bandit data presents fundamental challenges owing to adaptive sampling, which violates the independence assumptions underlying classical asymptotic theory.
arXiv Machine Learning
Aug 18
Online Convex Optimization with Dueling Feedback
arXiv:2608. 15050v1 Announce Type: new Abstract: We study online convex optimization with dueling (pairwise comparison) feedback, where the learner observes only a binary preference between two queried points.
arXiv Machine Learning
Jul 1
Constrained Online Convex Optimization without Slater's Condition
arXiv:2606. 31480v1 Announce Type: new Abstract: We study constrained online convex optimization with adversarial losses and stochastic or adversarial constraints.
arXiv Machine Learning
Aug 18
Last-Iterate Analyses of FTRL with the 1/2-Tsallis Entropy in Stochastic Bandits
arXiv:2510. 22819v3 Announce Type: replace Abstract: The convergence analysis of online learning algorithms is central to machine learning theory, where the last-iterate convergence is particularly important, as it captures the learner's actual decisions and describes the evolution of the learning process over time.
arXiv Machine Learning
Sep 30
Dynamic Regret via Discounted-to-Dynamic Reduction with Applications to Curved Losses and Adam Optimizer
arXiv:2602.08372v2 Announce Type: replace Abstract: We study dynamic regret minimization in non-stationary online learning, with a primary focus on follow-the-regularized-leader (FTRL) methods. FTRL...
arXiv Machine Learning
Sep 30
Provable Benefits of Regularization: Fast Rates for Adversarial Imitation Learning
The paper introduces Dually Regularized AIL, a model‑free algorithm for adversarial imitation learning that jointly applies KL policy regularization and a quadratic reward penalty based on expert and learner occupancies. It proves fast convergence rates, achieving a ×O(1/K+1/N) bound on the regularized imitation gap in finite‑horizon MDPs with general function approximation, and establishes the first algorithm to attain ×O(1/ε) sample complexity in both expert demonstrations and online interactions for this regularized objective.