Research
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 i
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 is important for curved losses and for understanding adaptive optimizers such as Adam, yet existing dynamic regret analyses are less explored for FTRL. To address this, we build on the discounted-to-dynamic reduction and present a modular way to obtain dynamic regret bounds of FTRL-related problems. Specifically, we focus on two representative curved losses: linear regression and logistic regression. Our method not only simplifies existing proofs for the optimal dynamic regret of online linear regression, but also yields new dynamic regret guarantees for online logistic regression. Beyond online convex optimization, we apply the reduction to analyze the Adam optimizers, obtaining optimal convergence rates in stochastic, non-convex, and non-smooth settings. The reduction also enables a more detailed treatment of Adam with two discount parameters (eta_1,eta_2), leading to new results for both clipped and clip-free variants of Adam optimizers.
Related
- From Switching to Dynamic Regret: A Simple Reduction via Unbiased Random Sequences
- Dynamic Regret for Online Regression in RKHS via Discounted VAW and Subspace Approximation
- Exact-Form Regret for Gradient Descent, Mirror Descent and Follow-the-Regularized-Leader
- Dynamic Regret in Online Convex Optimization with Indicator Switching Costs
Source: arXiv cs.LG | 2026-09-30