Copertina

Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Yu-Jie, Zhao, Peng, Sugiyama, Masashi
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Dynamic Regret via Discounted-to-Dynamic Reduction with Applications to Curved Losses and Adam Optimizer
di: Xie, Yan-Feng, et al.
Pubblicazione: (2026)

Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update
di: Zhang, Yu-Jie, et al.
Pubblicazione: (2025)

Adapting to Continuous Covariate Shift via Online Density Ratio Estimation
di: Zhang, Yu-Jie, et al.
Pubblicazione: (2023)

Adaptivity and Non-stationarity: Problem-dependent Dynamic Regret for Online Convex Optimization
di: Zhao, Peng, et al.
Pubblicazione: (2021)

Mixability of Integral Losses: a Key to Efficient Online Aggregation of Functional and Probabilistic Forecasts
di: Korotin, Alexander, et al.
Pubblicazione: (2019)

Efficient Methods for Non-stationary Online Learning
di: Zhao, Peng, et al.
Pubblicazione: (2023)

On Symmetric Losses for Robust Policy Optimization with Noisy Preferences
di: Nishimori, Soichiro, et al.
Pubblicazione: (2025)

Improved Dynamic Regret for Online Frank-Wolfe
di: Wan, Yuanyu, et al.
Pubblicazione: (2023)

Data-dependent Exploration for Online Reinforcement Learning from Human Feedback
di: Zhang, Zhen-Yu, et al.
Pubblicazione: (2026)

Online Structured Prediction with Fenchel--Young Losses and Improved Surrogate Regret for Online Multiclass Classification with Logistic Loss
di: Sakaue, Shinsaku, et al.
Pubblicazione: (2024)

Gradient-Variation Regret Bounds for Unconstrained Online Learning
di: Zhao, Yuheng, et al.
Pubblicazione: (2026)

Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary Dynamics
di: Zhang, Xinyu, et al.
Pubblicazione: (2024)

Offline Reinforcement Learning from Datasets with Structured Non-Stationarity
di: Ackermann, Johannes, et al.
Pubblicazione: (2024)

Improved Approximate Regret for Decentralized Online Continuous Submodular Maximization via Reductions
di: Wan, Yuanyu, et al.
Pubblicazione: (2026)

Riemannian Langevin Dynamics: Strong Convergence of Geometric Euler-Maruyama Scheme
di: Zhan, Zhiyuan, et al.
Pubblicazione: (2026)

Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical
di: Wang, Wei, et al.
Pubblicazione: (2023)

Variance-Dependent Regret Bounds for Non-stationary Linear Bandits
di: Wang, Zhiyong, et al.
Pubblicazione: (2024)

Improved Kernel Alignment Regret Bound for Online Kernel Learning
di: Li, Junfan, et al.
Pubblicazione: (2022)

Logarithmic Regret for Online KL-Regularized Reinforcement Learning
di: Zhao, Heyang, et al.
Pubblicazione: (2025)

Achieving Optimal Static and Dynamic Regret Simultaneously in Bandits with Deterministic Losses
di: Qian, Jian, et al.
Pubblicazione: (2026)

Mixture of Online and Offline Experts for Non-stationary Time Series
di: Zhao, Zhilin, et al.
Pubblicazione: (2022)

Improved Regret Bounds for Online Fair Division with Bandit Learning
di: Schiffer, Benjamin, et al.
Pubblicazione: (2025)

A Fast Algorithm for the Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit
di: Nakamura, Shintaro, et al.
Pubblicazione: (2023)

Enriching Disentanglement: From Logical Definitions to Quantitative Metrics
di: Zhang, Yivan, et al.
Pubblicazione: (2023)

Robust Multi-View Learning via Representation Fusion of Sample-Level Attention and Alignment of Simulated Perturbation
di: Xu, Jie, et al.
Pubblicazione: (2025)

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

Reinforcement Learning with Options and State Representation
di: Ghriss, Ayoub, et al.
Pubblicazione: (2024)

VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction
di: Cai, Xin-Qiang, 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)

Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning
di: Chen, Baiyuan, et al.
Pubblicazione: (2025)

Improved Regret in Stochastic Decision-Theoretic Online Learning under Differential Privacy
di: Wu, Ruihan, et al.
Pubblicazione: (2025)

Multi-Player Approaches for Dueling Bandits
di: Raveh, Or, et al.
Pubblicazione: (2024)

A Category-theoretical Meta-analysis of Definitions of Disentanglement
di: Zhang, Yivan, et al.
Pubblicazione: (2023)

VEC-SBM: Optimal Community Detection with Vectorial Edges Covariates
di: Braun, Guillaume, et al.
Pubblicazione: (2024)

Revisiting Weighted Strategy for Non-stationary Parametric Bandits and MDPs
di: Wang, Jing, et al.
Pubblicazione: (2026)

Evolving Graph Learning for Out-of-Distribution Generalization in Non-stationary Environments
di: Sun, Qingyun, et al.
Pubblicazione: (2025)

Alternating Regret for Online Convex Optimization
di: Hait, Soumita, et al.
Pubblicazione: (2025)

Towards Scalable Oversight via Partitioned Human Supervision
di: Yin, Ren, et al.
Pubblicazione: (2025)

Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs
di: Li, Long-Fei, et al.
Pubblicazione: (2024)

Practical estimation of the optimal classification error with soft labels and calibration
di: Ushio, Ryota, et al.
Pubblicazione: (2025)