Search Results for author:
Found 7 papers, 3 papers with code
Maximum Entropy Model Correction in Reinforcement Learning
We propose and theoretically analyze an approach for planning with an approximate model in reinforcement learning that can reduce the adverse impact of model error.
Efficient and Accurate Optimal Transport with Mirror Descent and Conjugate Gradients
We design a novel algorithm for optimal transport by drawing from the entropic optimal transport, mirror descent and conjugate gradients literatures.
Approximate Policy Iteration with Bisimulation Metrics
Based on these results, we design an API($\alpha$) procedure that employs conservative policy updates and enjoys better performance bounds than the naive API approach.
Towards Robust Bisimulation Metric Learning
Learned representations in deep reinforcement learning (DRL) have to extract task-relevant information from complex observations, balancing between robustness to distraction and informativeness to the policy.
Dependency parsing with structure preserving embeddings
We do so by casting dependency parsing as a tree embedding problem where we incorporate geometric properties of dependency trees in the form of training losses within a graph-based parser.
RankMI: A Mutual Information Maximizing Ranking Loss
We introduce an information-theoretic loss function, RankMI, and an associated training algorithm for deep representation learning for image retrieval.
Dynamic Scheduling of MPI-based Distributed Deep Learning Training Jobs
In this paper, we analyze the math behind ring architectures and make an informed adaptation of dynamic scheduling to ring architectures.
