1.4k citations · 18.4k across the 482 of their papers we have counts for
4 papers · 2 filters
On the Validation of Gibbs Algorithms: Training Datasets, Test Datasets and their Aggregation
Samir M. Perlaza, Iñaki Esnaola, Gaetan Bisson +1
The dependence on training data of the Gibbs algorithm (GA) is analytically characterized. By adopting the expected empirical risk as the performance metric, the sensitivity of the…
Efficient Reinforcement Learning with Impaired Observability: Learning to Act with Delayed and Missing State Observations
Minshuo Chen, Jie Meng, Yu Bai +3
In real-world reinforcement learning (RL) systems, various forms of {\it impaired observability} can complicate matters. These situations arise when an agent is unable to observe t…
Reconstructing Graph Diffusion History from a Single Snapshot
Ruizhong Qiu, Dingsu Wang, Lei Ying +3
Diffusion on graphs is ubiquitous with numerous high-impact applications. In these applications, complete diffusion histories play an essential role in terms of identifying dynamic…
Fast Computation of Optimal Transport via Entropy-Regularized Extragradient Methods
Gen Li, Yanxi Chen, Yu Huang +3
Efficient computation of the optimal transport distance between two distributions serves as an algorithm subroutine that empowers various applications. This paper develops a scalab…