3 papers
cs.LG2026
Theory on Attention Dynamics for Out-of-Distribution In-Context Learning
Junze Deng, Daouda Sow, Sen Lin +1
Transformers have demonstrated remarkable in-context learning (ICL) capabilities, enabling them to perform new tasks without additional fine-tuning. However, their performance ofte…
cs.LG2025
Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective
Junze Deng, Qinhang Wu, Peizhong Ju +3
Rehearsal-based methods have shown superior performance in addressing catastrophic forgetting in continual learning (CL) by storing and training on a subset of past data alongside…
cs.LG2024
Sample Complexity Characterization for Linear Contextual MDPs
Junze Deng, Yuan Cheng, Shaofeng Zou +1
Contextual Markov decision processes (CMDPs) describe a class of reinforcement learning problems in which the transition kernels and reward functions can change over time with diff…