Imagen de Portada

Immediate Derivatives Suffice for Online Recurrent Adaptation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Merin, Aur Shalev
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Massive Redundancy in Gradient Transport Enables Sparse Online Learning
por: Merin, Aur Shalev
Publicado: (2026)

Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approach
por: Bar, Yarin, et al.
Publicado: (2024)

Logarithmic Width Suffices for Robust Memorization
por: Egosi, Amitsour, et al.
Publicado: (2025)

Linear Bellman Completeness Suffices for Efficient Online Reinforcement Learning with Few Actions
por: Golowich, Noah, et al.
Publicado: (2024)

Querying Kernel Methods Suffices for Reconstructing their Training Data
por: Barzilai, Daniel, et al.
Publicado: (2025)

When Does Confidence-Based Cascade Deferral Suffice?
por: Jitkrittum, Wittawat, et al.
Publicado: (2023)

Adaptive Regret for Bandits Made Possible: Two Queries Suffice
por: Lu, Zhou, et al.
Publicado: (2024)

Feature Augmentation of GNNs for ILPs: Local Uniqueness Suffices
por: Han, Qingyu, et al.
Publicado: (2025)

Subsampling Suffices for Adaptive Data Analysis
por: Blanc, Guy
Publicado: (2023)

Prediction-Powered Semi-Supervised Learning with Online Power Tuning
por: Shoham, Noa, et al.
Publicado: (2025)

Transformers on Markov Data: Constant Depth Suffices
por: Rajaraman, Nived, et al.
Publicado: (2024)

IP-Basis PINNs: Efficient Multi-Query Inverse Parameter Estimation
por: Manor, Shalev, et al.
Publicado: (2025)

Caravan MultiMet: Extending Caravan with Multiple Weather Nowcasts and Forecasts
por: Shalev, Guy, et al.
Publicado: (2024)

A Unified Framework for Simultaneous Parameter and Function Discovery in Differential Equations
por: Manor, Shalev, et al.
Publicado: (2025)

Rethinking Multi-Label Node Classification: Do Tuned Classic GNNs Suffice?
por: Xiao, Yuxuan, et al.
Publicado: (2026)

The Multiple Ticket Hypothesis: Random Sparse Subnetworks Suffice for RLVR
por: Adewuyi, Israel, et al.
Publicado: (2026)

LLM-Generated Explanations Do Not Suffice for Ultra-Strong Machine Learning
por: Ai, Lun, et al.
Publicado: (2025)

Federated Offline Reinforcement Learning: Collaborative Single-Policy Coverage Suffices
por: Woo, Jiin, et al.
Publicado: (2024)

Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear $q^π$-Realizability and Concentrability
por: Tkachuk, Volodymyr, et al.
Publicado: (2024)

How Many Domains Suffice for Domain Generalization? A Tight Characterization via the Domain Shattering Dimension
por: Dwork, Cynthia, et al.
Publicado: (2025)

Recurrent Memory for Online Interdomain Gaussian Processes
por: Chen, Wenlong, et al.
Publicado: (2025)

READ: Recurrent Adaptation of Large Transformers
por: Nguyen, John, et al.
Publicado: (2023)

Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning
por: Lee, Yu-Ang, et al.
Publicado: (2026)

Testing For Distribution Shifts with Conditional Conformal Test Martingales
por: Shaer, Shalev, et al.
Publicado: (2026)

Online Feature Updates Improve Online (Generalized) Label Shift Adaptation
por: Wu, Ruihan, et al.
Publicado: (2024)

Research Program: Theory of Learning in Dynamical Systems
por: Hazan, Elad, et al.
Publicado: (2025)

Auction-Based Online Policy Adaptation for Evolving Objectives
por: Shabadi, Guruprerana, et al.
Publicado: (2026)

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently
por: Zhang, Yuanhe, et al.
Publicado: (2025)

S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models
por: Young, Jack
Publicado: (2026)

Contextual Plackett-Luce: An Efficient Neural Model for Probabilistic Sequence Selection under Ambiguity
por: Mizrachi, Noam, et al.
Publicado: (2026)

Untangling Lariats: Subgradient Following of Variationally Penalized Objectives
por: Mo, Kai-Chia, et al.
Publicado: (2024)

Improving Sequential Query Recommendation with Immediate User Feedback
por: Parambath, Shameem A Puthiya, et al.
Publicado: (2022)

Online Adaptation for Enhancing Imitation Learning Policies
por: Malato, Federico, et al.
Publicado: (2024)

Provably Efficient Offline-to-Online Value Adaptation with General Function Approximation
por: Li, Shangzhe, et al.
Publicado: (2026)

Online Conformal Inference with Retrospective Adjustment for Faster Adaptation to Distribution Shift
por: Jun, Jungbin, et al.
Publicado: (2025)

METER: A Dynamic Concept Adaptation Framework for Online Anomaly Detection
por: Zhu, Jiaqi, et al.
Publicado: (2023)

Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization
por: Fang, Zheng, et al.
Publicado: (2026)

Robust Unscented Kalman Filtering via Recurrent Meta-Adaptation of Sigma-Point Weights
por: Majewski, Kenan, et al.
Publicado: (2026)

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

Overcoming Negative Transfer by Online Selection: Distant Domain Adaptation for Fault Diagnosis
por: Wang, Ziyan, et al.
Publicado: (2024)