Copertina

Dynamic Regret via Discounted-to-Dynamic Reduction with Applications to Curved Losses and Adam Optimizer

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xie, Yan-Feng, Zhang, Yu-Jie, Zhao, Peng, Zhou, Zhi-Hua
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Optimization and Control
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Adaptivity and Universality: Problem-dependent Universal Regret for Online Convex Optimization
di: Zhao, Peng, et al.
Pubblicazione: (2025)

Gradient-Variation Online Learning under Generalized Smoothness
di: Xie, Yan-Feng, et al.
Pubblicazione: (2024)

Distributed Online Bandit Nonconvex Optimization with One-Point Residual Feedback via Dynamic Regret
di: Hua, Youqing, et al.
Pubblicazione: (2024)

Understanding Adam Optimizer via Online Learning of Updates: Adam is FTRL in Disguise
di: Ahn, Kwangjun, et al.
Pubblicazione: (2024)

Adam-SHANG: A Convergent Adam-Type Method for Stochastic Smooth Convex Optimization
di: Yu, Yaxin, et al.
Pubblicazione: (2026)

Optimistic Online-to-Batch Conversions for Accelerated Convergence and Universality
di: Yan, Yu-Hu, et al.
Pubblicazione: (2025)

Universal Online Learning with Gradient Variations: A Multi-layer Online Ensemble Approach
di: Yan, Yu-Hu, et al.
Pubblicazione: (2023)

A Simple, Optimal and Efficient Algorithm for Online Exp-Concave Optimization
di: Wang, Yi-Han, et al.
Pubblicazione: (2025)

An Equivalence Between Static and Dynamic Regret Minimization
di: Jacobsen, Andrew, et al.
Pubblicazione: (2024)

Dynamic Controlled Variables Based Dynamic Self-Optimizing Control
di: Zhou, Chenchen, et al.
Pubblicazione: (2026)

Provable Adaptivity of Adam under Non-uniform Smoothness
di: Wang, Bohan, et al.
Pubblicazione: (2022)

Implicit Bias of AdamW: $\ell_\infty$ Norm Constrained Optimization
di: Xie, Shuo, et al.
Pubblicazione: (2024)

On the Convergence of Adam-Type Algorithm for Bilevel Optimization under Unbounded Smoothness
di: Gong, Xiaochuan, et al.
Pubblicazione: (2025)

Online Convex Optimization with Heavy Tails: Old Algorithms, New Regrets, and Applications
di: Liu, Zijian
Pubblicazione: (2025)

Convergence Guarantees for RMSProp and Adam in Generalized-smooth Non-convex Optimization with Affine Noise Variance
di: Zhang, Qi, et al.
Pubblicazione: (2024)

Wasserstein Distributionally Robust Regret Optimization
di: Fiechtner, Lukas-Benedikt, et al.
Pubblicazione: (2025)

Adam-HNAG: A Convergent Reformulation of Adam with Accelerated Rate
di: Yu, Yaxin, et al.
Pubblicazione: (2026)

Adam Converges Without Any Modification On Update Rules
di: Zhang, Yushun, et al.
Pubblicazione: (2026)

Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback
di: Barakat, Anas, et al.
Pubblicazione: (2026)

HomeAdam: Adam and AdamW Algorithms Sometimes Go Home to Obtain Better Provable Generalization
di: Huang, Feihu, et al.
Pubblicazione: (2026)

Risk-Sensitive Q-Learning in Continuous Time with Application to Dynamic Portfolio Selection
di: Xie, Chuhan
Pubblicazione: (2025)

Regret of exploratory policy improvement and $q$-learning
di: Tang, Wenpin, et al.
Pubblicazione: (2024)

Adam-family Methods for Nonsmooth Optimization with Convergence Guarantees
di: Xiao, Nachuan, et al.
Pubblicazione: (2023)

On Convergence of Adam for Stochastic Optimization under Relaxed Assumptions
di: Hong, Yusu, et al.
Pubblicazione: (2024)

Asymptotically Optimal Regret for Black-Box Predict-then-Optimize
di: Tan, Samuel, et al.
Pubblicazione: (2024)

No-Regret Gaussian Process Optimization of Time-Varying Functions
di: Mauduit, Eliabelle, et al.
Pubblicazione: (2025)

Small Gradient Norm Regret for Online Convex Optimization
di: Gao, Wenzhi, et al.
Pubblicazione: (2026)

Stochastic Gradient Langevin Dynamics with Variance Reduction
di: Huang, Zhishen, et al.
Pubblicazione: (2021)

On the Convergence of Adam under Non-uniform Smoothness: Separability from SGDM and Beyond
di: Wang, Bohan, et al.
Pubblicazione: (2024)

Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness
di: Zhao, Yuheng, et al.
Pubblicazione: (2025)

Are Convex Optimization Curves Convex?
di: Barzilai, Guy, et al.
Pubblicazione: (2025)

Adapprox: Adaptive Approximation in Adam Optimization via Randomized Low-Rank Matrices
di: Zhao, Pengxiang, et al.
Pubblicazione: (2024)

Dynamic Range Reduction via Branch-and-Bound
di: Gerlach, Thore, et al.
Pubblicazione: (2024)

Towards Fully Parameter-Free Stochastic Optimization: Grid Search with Self-Bounding Analysis
di: Zhao, Yuheng, et al.
Pubblicazione: (2026)

Regret Bounds for Expected Improvement Algorithms in Gaussian Process Bandit Optimization
di: Tran-The, Hung, et al.
Pubblicazione: (2022)

From Adam to Adam-Like Lagrangians: Second-Order Nonlocal Dynamics
di: Heredia, Carlos
Pubblicazione: (2026)

Efficient Sign-Based Optimization: Accelerating Convergence via Variance Reduction
di: Jiang, Wei, et al.
Pubblicazione: (2024)

Modified Meta-Thompson Sampling for Linear Bandits and Its Bayes Regret Analysis
di: Li, Hao, et al.
Pubblicazione: (2024)

LEVDA: Latent Ensemble Variational Data Assimilation via Differentiable Dynamics
di: Si, Phillip, et al.
Pubblicazione: (2026)

Improved Regret Bound for Safe Reinforcement Learning via Tighter Cost Pessimism and Reward Optimism
di: Yu, Kihyun, et al.
Pubblicazione: (2024)