Learning & Optimization in Systems & Control
L&O reading group
We read and present some of the latest (e.g. preprint or early access) papers on learning, optimization, and game theory that are affine with system and control theory, to appear in top journals (e.g., SIOPT, SICON, Automatica, TAC, TNNLS) and conferences (e.g., ICLR, NIPS, ICML, CDC)
Meeting ID:
Passcode:
Fall 2021, Friday, 15:00 (CET)
presenter
date
paper
Barbara Franci
October 8
Liu et al. - Distributionally robust equilibrium for continuous games: Nash and Stackelberg models
Sergio Grammatico
October 22
Romano, Pavel - An inexact-penalty method for GNE seeking in games with dynamic agents
Wicak Ananduta
November 5
Feyzmahdavian, Johansson - Asynchronous iterations in optimization: New sequence results and sharper algorithmic guarantees
Emilio Benenati
November 19
Belgioioso et al. - Sampled-data online feedback equilibrium seeking: Stability and tracking
Suad Krilasevic
December 10
X. Cai et al. - Distributed continuous-time strategy-updating rules for noncooperative games with discrete-time communication
Luyao Zhang
January 14
M. Wang et al. - Game-theoretic planning for self-driving cars in multivehicle competitive scenarios
Spring 2021
Mattia Bianchi
February 12
Hassan-Moghaddam, Jovanović - Proximal gradient flow and Douglas-Rachford splitting dynamics
Barbara Franci
February 26
Verbree, Cherukuri - Stochastic approximation for CVaR-based variational inequalities
Sergio Grammatico
March 12
Gao, Pavel - On passivity, reinforcement learning, and higher order learning in multiagent finite games
Aitazaz Ali Raja
March 26
Muthirayan, Parvania, Khargonekar - Online algorithms for dynamic matching markets in power distribution systems
Peyman M. Esfahani
April 9
Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
Wicak Ananduta
April 23
Camisa, Notarnicola, Notarstefano - Distributed primal decomposition for large-scale MILPs
Emilio Benenati
May 7
Bianchin, Cortes, Poveda, Dall'Anese - Time-varying optimization of LTI systems via projected primal-dual gradient flows
Suad Krilasevic
May 21
Garg, Baranwal, Gupta, Vasudevan, Panagou - Fixed-time stable proximal dynamical system for solving mixed variational inequality problems
Gyula Max
June 4
Block, Yuval Dagan and Alexander Rakhlin - Majorizing Measures, Sequential Complexities, and Online Learning
Pedro Zattoni Scroccaro
June 18
Agarwal, Bullins, Hazan, Kakade, Singh - Online control with adversarial disturbances
Emilio Benenati
July 9
Bastianello, Dall'Anese - Distributed and inexact proximal gradient method for online convex optimization