Cover Image

Reactivation: Empirical NTK Dynamics Under Task Shifts

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Yuzhi, Chen, Zixuan, Zhang, Zirui, Liu, Yufei, Lanzillotta, Giulia
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Feature Identification via the Empirical NTK
by: Lin, Jennifer
Published: (2025)

Heads collapse, features stay: Why Replay needs big buffers
by: Lanzillotta, Giulia, et al.
Published: (2025)

NTK-Guided Few-Shot Class Incremental Learning
by: Liu, Jingren, et al.
Published: (2024)

The Importance of Being Lazy: Scaling Limits of Continual Learning
by: Graldi, Jacopo, et al.
Published: (2025)

Revisiting Knowledge Distillation: The Hidden Role of Dataset Size
by: Lanzillotta, Giulia, et al.
Published: (2025)

Local vs Global continual learning
by: Lanzillotta, Giulia, et al.
Published: (2024)

Rethinking Distribution Shifts: Empirical Analysis and Inductive Modeling for Tabular Data
by: Wang, Tianyu, et al.
Published: (2023)

An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift
by: Karouzos, Constantinos, et al.
Published: (2026)

On the Empirical Complexity of Reasoning and Planning in LLMs
by: Kang, Liwei, et al.
Published: (2024)

Random at First, Fast at Last: NTK-Guided Fourier Pre-Processing for Tabular DL
by: Sergazinov, Renat, et al.
Published: (2025)

Shortcut Features as Top Eigenfunctions of NTK: A Linear Neural Network Case and More
by: Lim, Jinwoo, et al.
Published: (2026)

Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity
by: Joudaki, Amir, et al.
Published: (2025)

Causal Pre-training Under the Fairness Lens: An Empirical Study of TabPFN
by: Liu, Qinyi, et al.
Published: (2026)

Are Your Reasoning Models Reasoning or Guessing? A Mechanistic Analysis of Hierarchical Reasoning Models
by: Ren, Zirui, et al.
Published: (2026)

Towards Collaborative Fairness in Federated Learning Under Imbalanced Covariate Shift
by: Yu, Tianrun, et al.
Published: (2025)

State Regularized Policy Optimization on Data with Dynamics Shift
by: Xue, Zhenghai, et al.
Published: (2023)

Linear $Q$-Learning Does Not Diverge in $L^2$: Convergence Rates to a Bounded Set
by: Liu, Xinyu, et al.
Published: (2025)

Scrutinize What We Ignore: Reining In Task Representation Shift Of Context-Based Offline Meta Reinforcement Learning
by: Zhang, Hai, et al.
Published: (2024)

Harmonizing Human Insights and AI Precision: Hand in Hand for Advancing Knowledge Graph Task
by: Wang, Shurong, et al.
Published: (2024)

Connecting NTK and NNGP: A Unified Theoretical Framework for Wide Neural Network Learning Dynamics
by: Avidan, Yehonatan, et al.
Published: (2023)

Which Graph Shift Operator? A Spectral Answer to an Empirical Question
by: Abbahaddou, Yassine
Published: (2026)

StaTS: Spectral Trajectory Schedule Learning for Adaptive Time Series Forecasting with Frequency Guided Denoiser
by: Zhang, Jintao, et al.
Published: (2026)

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited
by: Agrawal, Rishabh, et al.
Published: (2026)

Towards Understanding Link Predictor Generalizability Under Distribution Shifts
by: Revolinsky, Jay, et al.
Published: (2024)

Robust Calibration For Improved Weather Prediction Under Distributional Shift
by: Gilda, Sankalp, et al.
Published: (2024)

DFWLayer: Differentiable Frank-Wolfe Optimization Layer
by: Liu, Zixuan, et al.
Published: (2023)

Data Uniformity Improves Training Efficiency and More, with a Convergence Framework Beyond the NTK Regime
by: Wang, Yuqing, et al.
Published: (2025)

GraphEdge: Dynamic Graph Partition and Task Scheduling for GNNs Computing in Edge Network
by: Xiao, Wenjing, et al.
Published: (2025)

IDOL: Meeting Diverse Distribution Shifts with Prior Physics for Tropical Cyclone Multi-Task Estimation
by: Yan, Hanting, et al.
Published: (2025)

Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts
by: Zhang, Zeyang, et al.
Published: (2024)

Finite Sample Analysis of Linear Temporal Difference Learning with Arbitrary Features
by: Xie, Zixuan, et al.
Published: (2025)

Towards Stable and Structured Time Series Generation with Perturbation-Aware Flow Matching
by: Zhang, Jintao, et al.
Published: (2025)

Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks
by: Liu, Yang, et al.
Published: (2025)

What Makes Looped Transformers Perform Better Than Non-Recursive Ones
by: Gong, Zixuan, et al.
Published: (2025)

Gradient Flow Drifting: Generative Modeling via Wasserstein Gradient Flows of KDE-Approximated Divergences
by: Cao, Jiarui, et al.
Published: (2026)

Robust Guided Diffusion for Offline Black-Box Optimization
by: Chen, Can Sam, et al.
Published: (2024)

On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length
by: Kim, Sunghwan, et al.
Published: (2026)

Conformal Prediction Under Distribution Shift: A COVID-19 Natural Experiment
by: Lee, Chorok
Published: (2026)

Robust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Space
by: Liu, Qianmei, et al.
Published: (2024)

Cross-model Fairness: Empirical Study of Fairness and Ethics Under Model Multiplicity
by: Sokol, Kacper, et al.
Published: (2022)