← Search

Junze Deng

2 accepted papers

2025

Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective

ICML 2025poster

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 new data in current task. While such a concurrent rehearsal strategy is widely used, it remains unclear if this approach…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

Sample Complexity Characterization for Linear Contextual MDPs

AISTATS 2024poster

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 different MDPs indexed by a context variable. While CMDPs serve as an important framework to model many real-world applicati…

Cited by 1Source ↗PDF ↗Scholar ↗