Parameter-Free Dynamic Regret under Heavy-Tailed Noise

arXiv:2607.27073 · cs.LG, cs.AI, math.OC · Submitted 2026-07-29 · Read on arXiv

cs.LG, cs.AI, math.OC

Submitted: 2026-07-29

Updated: 2026-09-22

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Regret — 110× in this paper · explained in 3 episodes
• Online Convex Optimization — 10× in this paper
• Non-stationarity — 3× in this paper · explained in 2 episodes
• Adaptivity — 2× in this paper · explained in 1 episode
• Loss Function — 2× in this paper · explained in 2 episodes
• Online Gradient Descent — 2× in this paper
• Core — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Online Convex Optimization with Heavy Tails: Old Algorithms, New Regrets, and Applications
• Online Learning: A Modern Introduction Using Convex Optimization

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks