3 citations · 5 across the 6 of their papers we have counts for
6 papers
A Truncated Newton Method for Optimal Transport
Mete Kemertas, Amir-massoud Farahmand, Allan D. Jepson
Developing a contemporary optimal transport (OT) solver requires navigating trade-offs among several critical requirements: GPU parallelization, scalability to high-dimensional pro…
Maximum Entropy Model Correction in Reinforcement Learning
Amin Rakhsha, Mete Kemertas, Mohammad Ghavamzadeh +1
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. If the model is…
Efficient and Accurate Optimal Transport with Mirror Descent and Conjugate Gradients
Mete Kemertas, Allan D. Jepson, Amir-massoud Farahmand
We propose Mirror Descent Optimal Transport (MDOT), a novel method for solving discrete optimal transport (OT) problems with high precision, by unifying temperature annealing in en…
Approximate Policy Iteration with Bisimulation Metrics
Mete Kemertas, Allan Jepson
Bisimulation metrics define a distance measure between states of a Markov decision process (MDP) based on a comparison of reward sequences. Due to this property they provide theore…
Towards Robust Bisimulation Metric Learning
Mete Kemertas, Tristan Aumentado-Armstrong
Learned representations in deep reinforcement learning (DRL) have to extract task-relevant information from complex observations, balancing between robustness to distraction and in…
Dynamic Scheduling of MPI-based Distributed Deep Learning Training Jobs
Tim Capes, Vishal Raheja, Mete Kemertas +1
There is a general trend towards solving problems suited to deep learning with more complex deep learning architectures trained on larger training sets. This requires longer comput…