10 papers
Resolving Endpoint Underfitting in Diffusion Bridges via Noise Alignment
Yurong Gao, Zicheng Zhang, Congying Han +2
Diffusion bridge models offer a powerful framework for connecting two data distributions, such as in image restoration and translation. Many existing methods learn this bridge by m…
Robust Accelerated Adaptive Search: High-Probability Complexity Bounds under Bounded-Moment Stochastic Oracles
Shunzhi Zhang, Shichen Liao, Congying Han +1
We study unconstrained smooth convex optimization under stochastic first- and zeroth-order oracles subject only to finite-moment bounds, naturally admitting persistent bias and hea…
Relating Checkpoint Update Probabilities to Momentum Parameters in Single-Loop Variance Reduction Methods
Hai Liu, Tiande Guo, Congying Han
We propose a single-loop variance-reduced acceleration framework, which relates checkpoint update probabilities to momentum parameters, for solving the composite general convex pro…
A Fast Anti-Jamming Cognitive Radar Deployment Algorithm Based on Reinforcement Learning
Wencheng Cai, Xuchao Gao, Congying Han +2
The fast deployment of cognitive radar to counter jamming remains a critical challenge in modern warfare, where more efficient deployment leads to quicker detection of targets. Exi…
On the Tension Between Optimality and Adversarial Robustness in Policy Optimization
Haoran Li, Jiayu Lv, Congying Han +5
Achieving optimality and adversarial robustness in deep reinforcement learning has long been regarded as conflicting goals. Nonetheless, recent theoretical insights presented in CA…
Mitigating Distribution Shift in Model-based Offline RL via Shifts-aware Reward Learning
Wang Luo, Haoran Li, Zicheng Zhang +4
Model-based offline reinforcement learning trains policies using pre-collected datasets and learned environment models, eliminating the need for direct real-world environment inter…