Mohammad Sadegh Talebi


  Home    Publications    Teaching    Curriculum Vitae 



PUBLICATIONS

Copyright Notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

You are free to re-use the slides given here, provided that you provide a link to this website.

My Google Scholar page.

Home pages of some of my co-authors are listed below:

Alexandre Proutiere, Richard Combes, Mikael Johansson, Odalric-Ambrym Maillard, Mohammad H. Hajiesmaili, Marc Lelarge, Ahmad Khonsari, Bahram Alinia, Hosein Shafiei, Zhenhua Zou, Mahsa Asadi, Hippolyte Bourel, Mahdi Kefayati,


PREPRINTS
  • Average-reward reinforcement learning in tabular MDPs revisited
    with H. Bourel and O.-A. Maillard.
    Submitted.

JOURNAL PAPERS

  • Learning proportionally fair allocations with low regret
    with A. Proutiere.
    Proceedings of the ACM on Measurement and Analysis of Computing Systems, Volume 2, Issue 2, June 2018, Article No. 36 [doi].

  • Stochastic online shortest path routing: The value of feedback
    with Z. Zou, R. Combes, A. Proutiere, and M. Johansson.
    IEEE Transactions on Automatic Control 63(4): 915-930 (2018) [doi] (Longer version on [arXiv]).

  • Multi-period network rate allocation with end-to-end delay constraints
    with M. H. Hajiesmaili and A. Khonsari.
    IEEE Transactions on Control of Network Systems 5(3): 1087-1097 (2018) [doi].

  • Joint multipath rate control and scheduling for SVC streams in wireless mesh networks
    with M. H. Hajiesmaili and A. Khonsari.
    International Journal of Ad Hoc and Ubiquitous Computing 15(4): 239-251 (2014) [doi].

  • Maximizing quality of aggregation in delay-constrained wireless sensor networks
    with B. Alinia, H. Yousefi, and A. Khonsari.
    IEEE Communications Letters 17(11): 2084-2087 (2013) [doi].

  • Cost-aware monitoring of network-wide aggregates in wireless sensor networks
    with A. Khonsari, A. Mohtasham, and A. Abbasi.
    Computer Networks 55(6): 1276-1290 (2011) [doi].

  • Utility-proportional bandwidth sharing for multimedia transmission supporting scalable video coding
    with A. Khonsari and M. H. Hajiesmaili.
    Computer Communications 33(13): 1543-1556 (2010) [doi].

CONFERENCE PAPERS

  • Learning multiple Markov chains via adaptive allocation
    with O.-A. Maillard.
    Accepted to NeurIPS 2019 [arXiv].

  • Model-based reinforcement learning exploiting state-action equivalence
    with M. Asadi, H. Bourel, and O.-A. Maillard.
    Accepted to Asian Conference on Machine Learning (ACML), 2019 [doi] [arXiv]. (Best Student Paper Award).

  • Learning proportionally fair allocations with low regret
    with A. Proutiere.
    Proc. ACM SIGMETRICS 2018 [doi] [slides].

  • Competitive online scheduling algorithms with applications in deadline-constrained EV charging
    with B. Alinia, M. H. Hajiesmaili, A. Yekkehkhany, and N. Crespi.
    Proc. IEEE/ACM International Symposium on Quality of Service (IWQoS), 2018 [doi].

  • Variance-aware regret bounds for undiscounted reinforcement learning in MDPs
    with O.-A. Maillard (equal contribution).
    Proc. International Conference on Algorithmic Learning Theory (ALT), 2018 [arXiv] [slides].

  • An optimal algorithm for stochastic matroid bandit optimization
    with A. Proutiere.
    Proc. International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2016 [doi].

  • Combinatorial bandits revisited
    with R. Combes, A. Proutiere, and M. Lelarge.
    Advances in Neural Information Processing Systems 28 (NIPS), 2015 [pdf][doi][arXiv].

  • Utility-optimal dynamic rate allocation under average end-to-end delay requirements
    with M. H. Hajiesmaili and A. Khonsari.
    Proc. IEEE Conference on Decision and Control (CDC), 2015 [arXiv].

  • Spectrum bandit optimization
    with M. Lelarge and A. Proutiere.
    Proc. IEEE Information Theory Workshop (ITW), 2013 [doi][arXiv].

  • NUM-based rate allocation for streaming traffic via sequential convex programming
    with A. Sehati and A. Khonsari.
    Proc. IEEE International Conference on Communications (ICC), 2012 [doi].

  • Optimization bandwidth sharing for multimedia transmission supporting scalable video coding
    with A. Khonsari and M. H. Hajiesmaili.
    Proc. IEEE Conference on Local Computer Networks (LCN), 2009 [doi].

  • Source location anonymity for sensor networks
    with A. Abbasi and A. Khonsari.
    Proc. IEEE Consumer Communications and Networking Conference (CCNC), 2009 [doi].

  • Secure consensus averaging in sensor networks using random offsets
    with M. Kefayati, H. R. Rabiee, and B. H. Khalaj.
    Proc. ICT-MICC, 2007 [doi].

  • Adaptive consensus averaging for information fusion over sensor networks
    with M. Kefayati, B. H. Khalaj, and H. R. Rabiee.
    Proc. IEEE Conference on Mobile Ad-hoc and Sensor Systems (MASS), 2006 [doi].

THESES

  • Minimizing regret in combinatorial bandits and reinforcement learning
    Doctoral Thesis, Department of Automatic Control, KTH Royal Institute of Technology, Stockholm
    Defended on December 19, 2017 [thesis]
    Committee: R. Ortner (Montanuniversitat Leoben), Ch. Dimitrakakis (Chalmers), Y. Seldin (U of Copenhagen), X. Hu (KTH).

  • Online combinatorial optimization under bandit feedback
    Licentiate Thesis, Department of Automatic Control, KTH Royal Institute of Technology, Stockholm
    Defended on February 5, 2016 [thesis][slides].

TECHNICAL REPORTS

  • Uncoupled learning rules for seeking equilibria in repeated plays: An overview
    [arXiv].


top |
Last updated on October 2019.