3 papers
cs.LG2025
BSA: Ball Sparse Attention for Large-scale Geometries
Catalin E. Brita, Hieu Nguyen, Lohithsai Yadala Chanchu +2
Self-attention scales quadratically with input size, limiting its use for large-scale physical systems. Although sparse attention mechanisms provide a viable alternative, they are…
cs.LG2025
Optimal Classification Trees for Continuous Feature Data Using Dynamic Programming with Branch-and-Bound
Catalin E. Brita, Jacobus G. M. van der Linden, Emir DemiroviÄ
Computing an optimal classification tree that provably maximizes training performance within a given size limit, is NP-hard, and in practice, most state-of-the-art methods do not s…
cs.LG2024
SimuDICE: Offline Policy Optimization Through World Model Updates and DICE Estimation
Catalin E. Brita, Stephan Bongers, Frans A. Oliehoek
In offline reinforcement learning, deriving an effective policy from a pre-collected set of experiences is challenging due to the distribution mismatch between the target policy an…