5 papers · 1 filter
Last-Iterate Guarantees for Online Reinforcement Learning in Structured Constrained MDPs
Nam Phuong Tran, Trinh Ha Mai Huynh, Tuyen Pham Le +3
In safety-critical applications, deployment uses a single policy, whose performance and constraint satisfaction should hold directly rather than only for an average or mixture of t…
Unlocking Compositional Generalization in Continual Few-Shot Learning
Phu-Quy Nguyen-Lam, Phu-Hoa Pham, Dao Sy Duy Minh +3
Object-centric representations promise a key property for few-shot learning: Rather than treating a scene as a single unit, a model can decompose it into individual object-level pa…
MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Bound
Phu-Hoa Pham, Chi-Nguyen Tran, Nguyen Lam Phu Quy +3
Streaming decision trees are natural candidates for open-world continual learning, as they perform local updates, enjoy bounded memory, and static decision boundaries. Despite thes…
Safety Game: Inference-Time Alignment of Black-Box LLMs via Constrained Optimization
Tuan Nguyen, Long Tran-Thanh
Ensuring that large language models (LLMs) comply with safety requirements is a central challenge in AI deployment. Existing alignment approaches primarily operate during training,…
Identifying the Best Arm in the Presence of Global Environment Shifts
Phurinut Srisawad, Juergen Branke, Long Tran-Thanh
This paper formulates a new Best-Arm Identification problem in the non-stationary stochastic bandits setting, where the means of all arms are shifted in the same way due to a globa…