Image de couverture de livre

Agile Online Model Selection: Resolving Adaptation Lag via Safeguarded Large Learning Rates

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Takemura, Kei, Matsuno, Ryuta, Sakuma, Keita
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Improved Impossible Tuning and Lipschitz-Adaptive Universal Online Learning with Gradient Variations
par: Takemura, Kei, et autres
Publié: (2025)

Source Component Shift Adaptation via Offline Decomposition and Online Mixing Approach
par: Matsuno, Ryuta
Publié: (2025)

Backward Compatibility in Attributive Explanation and Enhanced Model Training Method
par: Matsuno, Ryuta
Publié: (2024)

Online Learning-guided Learning Rate Adaptation via Gradient Alignment
par: Jiang, Ruichen, et autres
Publié: (2025)

Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent
par: Chu, Ya-Chi, et autres
Publié: (2025)

Heterogeneous Domain Adaptation with Positive and Unlabeled Data
par: Mori, Junki, et autres
Publié: (2023)

Lag Selection for Univariate Time Series Forecasting using Deep Learning: An Empirical Study
par: Leites, José, et autres
Publié: (2024)

Budgeted Online Model Selection and Fine-Tuning via Federated Learning
par: Ghari, Pouya M., et autres
Publié: (2024)

On Prompt-Driven Safeguarding for Large Language Models
par: Zheng, Chujie, et autres
Publié: (2024)

Benign Overfitting under Learning Rate Conditions for $α$ Sub-exponential Input
par: Okudo, Kota, et autres
Publié: (2024)

Revisiting Dynamic Evaluation: Online Adaptation for Large Language Models
par: Rannen-Triki, Amal, et autres
Publié: (2024)

Kelp: A Streaming Safeguard for Large Models via Latent Dynamics-Guided Risk Detection
par: Li, Xiaodan, et autres
Publié: (2025)

SWaRL: Safeguard Code Watermarking via Reinforcement Learning
par: Javidnia, Neusha, et autres
Publié: (2026)

Improved Training Mechanism for Reinforcement Learning via Online Model Selection
par: Afshar, Aida, et autres
Publié: (2025)

Safety in Graph Machine Learning: Threats and Safeguards
par: Wang, Song, et autres
Publié: (2024)

Learning Exactly Linearizable Deep Dynamics Models
par: Moriyasu, Ryuta, et autres
Publié: (2023)

Overcoming Negative Transfer by Online Selection: Distant Domain Adaptation for Fault Diagnosis
par: Wang, Ziyan, et autres
Publié: (2024)

Toward Safer Diffusion Language Models: Discovery and Mitigation of Priming Vulnerability
par: Yamabe, Shojiro, et autres
Publié: (2025)

On the Identifiability of Regime-Switching Models with Multi-Lag Dependencies
par: Balsells-Rodas, Carles, et autres
Publié: (2026)

Progressive Safeguards for Safe and Model-Agnostic Reinforcement Learning
par: Omi, Nabil, et autres
Publié: (2024)

Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation
par: Halawi, Danny, et autres
Publié: (2024)

Provably Efficient and Agile Randomized Q-Learning
par: Wang, He, et autres
Publié: (2025)

Bayesian Online Model Selection
par: Afshar, Aida, et autres
Publié: (2026)

Classification with Conceptual Safeguards
par: Joren, Hailey, et autres
Publié: (2024)

Compressing Sign Information in DCT-based Image Coding via Deep Sign Retrieval
par: Suzuki, Kei, et autres
Publié: (2022)

Safeguarding Privacy: Privacy-Preserving Detection of Mind Wandering and Disengagement Using Federated Learning in Online Education
par: Bodonhelyi, Anna, et autres
Publié: (2026)

Learning Collective Variables from BioEmu with Time-Lagged Generation
par: Park, Seonghyun, et autres
Publié: (2025)

DOLCE: Decomposing Off-Policy Evaluation/Learning into Lagged and Current Effects
par: Tamano, Shu
Publié: (2025)

An Agile Adaptation Method for Multi-mode Vehicle Communication Networks
par: He, Shiwen, et autres
Publié: (2024)

Online Adaptation for Enhancing Imitation Learning Policies
par: Malato, Federico, et autres
Publié: (2024)

Online Laplace Model Selection Revisited
par: Lin, Jihao Andreas, et autres
Publié: (2023)

Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts
par: Sharma, Kartik, et autres
Publié: (2025)

Discovering Entity-Conditioned Lag Heterogeneity: A Lag-Gated Neural Audit Framework for Panel Time Series
par: Xu, Andi
Publié: (2026)

Selective Aggregation for Low-Rank Adaptation in Federated Learning
par: Guo, Pengxin, et autres
Publié: (2024)

Bayesian Models for Joint Selection of Features and Auto-Regressive Lags: Theory and Applications in Environmental and Financial Forecasting
par: Manna, Alokesh, et autres
Publié: (2025)

Online-LoRA: Task-free Online Continual Learning via Low Rank Adaptation
par: Wei, Xiwen, et autres
Publié: (2024)

Robust Deep Reinforcement Learning against Adversarial Behavior Manipulation
par: Yamabe, Shojiro, et autres
Publié: (2024)

Evaluating LLM Safety Under Repeated Inference via Accelerated Prompt Stress Testing
par: Broadwater, Keita
Publié: (2026)

Selection, Ensemble, and Adaptation: Advancing Multi-Source-Free Domain Adaptation via Architecture Zoo
par: Pei, Jiangbo, et autres
Publié: (2024)

Safe Reinforcement Learning using Action Projection: Safeguard the Policy or the Environment?
par: Markgraf, Hannah, et autres
Publié: (2025)