However, calculating the Laplacian spectrum can be expensive in a matrix base.

We study off-policy evaluation (OPE) in partially observable environments with complex observations, with the goal of developing estimators whose guarantee avoids exponential dependence on the horizon.

This paper explores the realm of infinite horizon average reward Constrained Markov Decision Processes (CMDPs).

In this work, we propose an innovative test-time poisoned sample detection framework that hinges on the in-terpretability of model predictions, grounded in the semantic meaning of inputs. We contend that triggers (e.g., infrequent words) are not supposed to fundamentally alter the underlying semantic meanings of poisoned samples as they want to

We compute the convergence rates of the RSVB approximate posterior and the corresponding optimal value.