Jia Yuan, Yu
Associate Professor, Concordia Institute of Information System Engineering.
1455 de Maisonneuve Blvd. West EV007.635
Montreal, Quebec H3G 1M8
||+1 514 848 2424 ext. 2873
I'm interested in data science and decision theory (machine learning, statistics, control, game theory, operations research), as well as applications to smart cities and Internet-connected devices.
I'm looking for undergraduate and graduate students to work on exciting projects involving a mix of theory, data, and prototype-building. If you have a strong background in mathematics or programming, then please feel free to email me your CV and a description of your interests.
- Nonhomogeneous Place-Dependent Markov Chains, Unsynchronised AIMD, and Network Utility Maximization, [arXiv].
- On the Design of Campus Parking Systems with QoS guarantees, [arXiv].
- A Fair Assignment of Drivers to Parking Lots, [arXiv].
- Functional Bandits, [arXiv].
- Congestion Management by Interval Signaling, [arXiv].
- Sensor Selection for Crowdsensing Dynamical Systems, with Francois Schnitzler and Shie Mannor, AISTATS 2015.
- Signaled Queueing, with Laura Brink and Robert Shorten, AAMAS 2015.
- Real-time Bidding-based Vehicle Sharing, with Yinlam Chow, AAMAS 2015.
- Asynchronous Algorithms for Network Utility Maximisation with a Single Bit, with Fabian Wirth, Sonja Stuedli, Martin Corless, and Robert Shorten, ECC 2015.
- A result for nonhomogeneous place-dependent Markov Chains arising in the study of the AIMD algorithm and its application to certain optimisation problems, with Fabian Wirth, Sonja Stuedli, Martin Corless, and Robert Shorten, Allerton 2014.
- Traffic Management using RTEC in OWL 2 RL, with Bernard Gorman and Jakub Marecek, ISWC 2014.
- Sample complexity of risk-averse bandit-arm selection, with Evdokia Nikolova, IJCAI 2013.
- Data-driven Distributionally Robust Polynomial Optimization, with Martin Mevissen and Emanuele Ragnoli, NIPS 2013.
- Minimizing risk measures in bandit problems, INFORMS APS 2013.
- Distributionally robust optimization for polynomial optimization problems, with Martin Mevissen and Emanuele Ragnoli, ISMP 2012.
- Mean Field Equilibria of Multiarmed Bandit Games, with Ramakrishna Gummadi, Ramesh Johari, EC 2012.
- Unimodal bandits, with Shie Mannor, ICML 2011.
- Lipschitz Bandits without the Lipschitz Constant, with Sebastien Bubeck and Gilles Stoltz, ALT 2011.
- Adaptive and Optimal Online Linear Regression on L1-balls, with Sebastien Gerchinovitz, ALT 2011.
- Arbitrarily Modulated Markov Decision Processes, with Shie Mannor, CDC 2009.
- Piecewise-stationary bandit problems with side observations, with Shie Mannor, ICML 2009.
- Online learning in Markov decision processes with arbitrarily changing rewards and transitions, with Shie Mannor, GameNets 2009.
- Markov decision processes with arbitrary reward processes, with Shie Mannor and Nahum Shimkin, EWRL 2008.
- Online learning with expert advice and finite-horizon constraints, with Branislav Kveton, Georgios Theocharous and Shie Mannor, AAAI 2008.
- A lazy approach to online learning with constraints, with Branislav Kveton, Georgios Theocharous and Shie Mannor, ISAIM 2008.
- Asymptotics of efficiency loss in competitive market mechanisms, with Shie Mannor, Infocom 2006.
- Signaling and obfuscation for congestion control, with Jakub Marecek and Robert Shorten. International Journal of Control [arXiv], 2015.
- Adaptive and Optimal Online Linear Regression on L1-balls, with Sebastien Gerchinovitz. Theoretical Computer Science, 2012.
- Markov decision processes with arbitrary reward processes, with Shie Mannor and Nahum Shimkin. Mathematics of Operations Research 34(3) [737-757], 2009.
- Online learning with sample path constraints, with Shie Mannor and John N. Tsitsiklis. Journal of Machine Learning Research 10(Mar):[569-590], 2009.
- Efficiency loss of market-based resource allocation with many participants, with Shie Mannor, IEEE Journal on Selected Areas in Communications 25(6), 1244-1259, 2007.
Game Theory [Winter 2017].
Math for CS [Fall 2016].
Supply Chain Management [Winter 2016].
Supply Chain Design [Fall 2015], [Fall 2016].
Machine Learning [Spring 2014 and 2015].