Publications and Preprints

• Bicausal Optimal Transport for Markov Chains via Dynamic Programming.
  Vrettos Moulos,
  to appear in the IEEE International Symposium on Information Theory (ISIT), 2021
  [arXiv]

• Finite-time Analysis of Round-Robin Kullback-Leibler Upper Confidence Bounds for Optimal Adaptive Allocation with Multiple Plays and Markovian Rewards.
  Vrettos Moulos,
  in proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS), 2020
  [arXiv]

• A Hoeffding Inequality For Finite State Markov Chains and its Applications to Markovian Bandits.
  Vrettos Moulos,
  in proceedings of the IEEE International Symposium on Information Theory (ISIT), 2020
  [arXiv]

• Optimal Best Markovian Arm Identification with Fixed Confidence.
  Vrettos Moulos,
  in proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS), 2019
  [arXiv]

• Optimal Chernoff and Hoeffding Bounds for Finite State Markov Chains.
  Vrettos Moulos and Venkat Anantharam,
  [arXiv]

• Concentration and Sequential Decision Making in Markovian Environments.
  Vrettos Moulos,
  PhD dissertation, UC Berkeley, 2020
  [disseration]