Walid Krichene
Publications
Sort by: Year, Journal/Conference
In preparation / in review
W. Krichene, M. Balandat, C. Tomlin, A. Bayen,
Dual Averaging on CompactlySupported Distributions and Application to NoRegret Learning on a Continuum
In preparation.
W. Krichene, A. Bayen, P. Bartlett.
A Lyapunov Approach to Accelerated FirstOrder Optimization in Continuous and Discrete Time.
In preparation.
M. Suarez Castillo, W. Krichene, A. Bayen,
On Social Optimal Routing Under Selfish Learning.
In review, Transactions on Contol of Network Systems (TCNS).
2016
K. Lam, W. Krichene, A. Bayen,
On Learning How Players Learn: Estimation of Learning Dynamics in the Routing Game.
International Conference on Cyber Physical Systems (ICCPS).
2015
W. Krichene, A. Bayen, P. Bartlett.
Accelerated Mirror Descent in Continuous and Discrete Time.
29th Annual Conference on Neural Information Processing Systems (NIPS).
Supplementary material.
W. Krichene, S. Krichene, A. Bayen.
Efficient Bregman Projections onto the Simplex
54th IEEE Conference on Decision and Control (CDC).
Code: github.com/walidk/BregmanProjection
W. Krichene, B. Drighes, A. Bayen.
Learning Nash Equilibria in Congestion Games
SIAM Journal on Control and Optimization.
SIAM epublication
S. Krichene, W. Krichene, R. Dong, A. Bayen,
Convergence of Heterogeneous Distributed Learning in Stochastic Routing Games
53rd Annual Allerton Conference on Communication, Control, and Computing.
R. Dong, W. Krichene, A. Bayen, S. Sastry,
Differential Privacy of Populations in the Routing Game
54th IEEE Conference on Decision and Control (CDC).
W. Krichene, M. Balandat, C. Tomlin, A. Bayen.
The Hedge Algorithm on a Continuum
International Conference on Machine Learning (ICML).
Talk
W. Krichene, S. Krichene, A. Bayen.
Convergence of Mirror Descent Dynamics in the Routing Game
European Control Conference (ECC).
2014
W. Krichene, B. Drighes, A. Bayen.
On the Convergence of NoRegret Learning in Selfsih Routing
International Conference on Machine Learning (ICML).
Supplementary material
Slides
B. Drighes, W. Krichene, A. Bayen.
Stability of Nash Equilibria in the Congestion Game under Replicator Dynamics
53rd IEEE Conference on Decision and Control (2014).
W. Krichene, J. Reilly, S. Amin, A. Bayen.
Stackelberg Routing on Parallel Networks with Horizontal Queues
IEEE Transactions on Automatic Control.
http://dx.doi.org/10.1109/TAC.2013.2289709
bib
J. Reilly, W. Krichene, M. Delle Monache, P. Goatin, A. Bayen.
Adjointbased optimization on a network of discretized scalar conservation law PDEs with applications to coordinated ramp metering
Journal of Optimization Theory and Applications (JOTA)
2013
Y. Jebbari, W. Krichene, J. Reilly, A. Bayen.
Stackelberg Thresholds on Parallel Networks with Horizontal Queues
52nd IEEE Conference on Decision and Control.
bib
F. Farokhi, W. Krichene, A. M. Bayen, K. H. Johansson.
A Heterogeneous Routing Game
51st Annual Allerton Conference on Communication, Control, and Computing.
bib
M. Delle Monache, J. Reilly, S. Samaranayake, W. Krichene, P. Goatin, A. Bayen.
A PDEODE Model for a Junction with Ramp Buffer
Accepted, SIAM Journal on Applied Mathematics.
SIAM epublication
bib
2012
W. Krichene, J. Reilly, S. Amin, A. Bayen.
Characterization and Computation of Nash Equilibria in Parallel Netwoks with Horizontal Queues
51st IEEE Conference on Decision and Control.
pdf bib
W. Krichene, J. Reilly, S. Amin, A. Bayen.
Stackelberg Routing on Parallel Networks with Horizontal Queues
51st IEEE Conference on Decision and Control.
pdf bib
Technical reports
M. Balandat, W. Krichene, C. P. Lam, K. K. Lam.
Robust PCA, theory and applications (Report for EE227A Introduction to convex optimization)
W. Krichene
Online learning on a continuum (Report for CS294 Learning in sequential decision problems)
scholar
arXiv
dblp
Selected talks and presentations
2015
Accelerated Mirror Descent in Continuous and Discrete Time.
Spotlight presentation, NIPS 2015. December 2015.
Distributed learning in routing games: convergence, estimation of player dynamics, and control.
Institute for Pure and Applied Mathematics, UCLA, November 18, 2015.
A Lyapunov Approach to FirstOrder Optimization in Continuous and Discrete Time.
Semiautonomous group meeting, Berkeley. October 30th, 2015.
Efficient Bregman Projections onto the Simplex.
54th IEEE Conference on Decision and Control, Osaka, Japan, December 16, 2015.
Distributed learning dynamics: Convergence in routing games and beyond.
KAUST Conference on HumanMachine Networks and Intelligent Infrastructure. October 7th, 2015.
Convergence of Heterogeneous Distributed Learning in Stochastic Routing Games.
53rd Allerton Conference on Communication, Control and Computing, October 1st, 2015.
Convergence of Mirror Descent Dynamics in the Routing Game.
European Control Conference, Linz, Austria, July 15, 2015.
The Hedge Algorithm on a Continuum.
International Conference on Machine Learning (ICML), Lille, France, July 8, 2015.
Talk
2014
Stability of Nash equilibria in the Congestion Game under Replicator Dynamics.
IEEE Conference on Decision and Control, Los Angeles, CA, December 15, 2014.
Online Learning in Distributed Multi Agent Systems.
Qualifying Exam Talk, Berkeley, CA, November 25, 2014.
Robust Convergence of Distributed Routing with Heterogeneous Population Dynamics.
Foundations of Reslient Cyber Physical Systems (FORCES), Washington DC, November 14, 2014.
poster
On the convergence of online learning in selfish routing.
ICML 2014. June 23, 2014.
Talk
Routing games  Stackelberg routing and online learning.
UCSB control seminar. Santa Barbara, May 30, 2014.
Learning in finite games and convex potential games.
Bayen group meeting. Berkeley, May 12, 2014.
2013
Stackelberg Thresholds on Parallel Networks with Horizontal Queues.
Talk given at the 52nd IEEE Conference on Decision and Control, in Florence, Italy, December 10, 2013.
A Heterogeneous Routing Game.
Talk given at the 51st Annual Allerton Conference on Communication, Control, and Computing, October 2, 2013.
Online learning in routing games.
Talk given at the network economics seminar at Berkeley, October 18 2013.
On convergence of online learning in routing games.
Talk given at the semiautonomous group meeting at Berkeley, September 13 2013.
2010  2012
Routing a subset of Drivers on a Highway Network under Noncooperative Response using Robust Stackelberg Routing.
Talk given at the Workshop on Robust and Stochastic Control Methods for Sustainable Engineering, 51st IEEE Conference on Decision and Control, Maui, Hawaii, December 14, 2012.
On Stackelberg Routing on Parallel Networks with Horizontal Queues.
Talk given at the 51st IEEE Conference on Decision and Control, Maui, Hawaii, December 13, 2012.
Adjointbased Control of Traffic Systems  Application to Ramp Metering.
Talk given with Samitha Samaranayake at the Connected Corridors research seminar, PATH (Partners for Advanced Transportation Tech nology), Berkeley, November 2012.
Travel Time Estimation using Approximate Belief States on a Hidden Markov Model.
Talk given at Mines Paristech, Paris, France, September 2010.
