Workshop
Bridging Game Theory and Deep Learning
Ioannis Mitliagkas · Gauthier Gidel · Niao He · Reyhane Askari Hemmat · Nika Haghtalab · N H · Simon Lacoste-Julien

Sat Dec 14th 08:00 AM -- 06:30 PM @ West Exhibition Hall A
Event URL: https://sgo-workshop.github.io/ »

Advances in generative modeling and adversarial learning gave rise to a recent surge of interest in differentiable two-players games, with much of the attention falling on generative adversarial networks (GANs). Solving these games introduces distinct challenges compared to the standard minimization tasks that the machine learning (ML) community is used to. A symptom of this issue is ML and deep learning (DL) practitioners using optimization tools on game-theoretic problems. Our NeurIPS 2018 workshop, "Smooth games optimization in ML", aimed to rectify this situation, addressing theoretical aspects of games in machine learning, their special dynamics, and typical challenges. For this year, we significantly expand our scope to tackle questions like the design of game formulations for other classes of ML problems, the integration of learning with game theory as well as their important applications. To that end, we have confirmed talks from Éva Tardos, David Balduzzi and Fei Fang. We will also solicit contributed posters and talks in the area.

08:15 AM Opening remarks (Short presentation)
08:30 AM Invited talk: Eva Tardos (Cornell) (Invited talk) Eva Tardos
09:00 AM Morning poster Spotlight (Spotlight)
09:30 AM Morning poster session -- coffee break (Poster session)
Alberto Marchesi, Andrea Celli, Olga Ohrimenko, Hugo Berard, Moksh Jain, Qihang Lin, Yan Yan, Brian McWilliams, Konstantin Mishchenko, Mert Çelikok, Jacob Abernethy, Mingrui Liu, Boli Fang, Shuang Li, Lisa Lee, David Fridovich-Keil, Yuanhao Wang, Christos Tsirigotis, Guojun Zhang, Adam Lerer, Elizabeth Bondi, Chi Jin, Tanner Fiez, Benjamin Chasnov, Andrew Bennett, Ryan D'Orazio, Gabriele Farina, Yair Carmon, Eric Mazumdar, Adam Ibrahim, Hongkai Zheng
11:00 AM Invited talk: David Balduzzi (DeepMind (Invited talk) David Balduzzi
11:30 AM Contributed talk: What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization? (Contributed talk) Chi Jin
12:00 PM Contributed talk: Characterizing Equilibria in Stackelberg Games (Contributed talk) Tanner Fiez
12:30 PM Lunch break (Break)
02:00 PM Invited talk: Fei Fang (CMU) (Invited talk) Fei Fang
02:30 PM Contributed talk: On Solving Local Minimax Optimization: A Follow-the-Ridge Approach (Contributed talk) Yuanhao Wang
03:00 PM Contributed talk: Exploiting Uncertain Real-Time Information from Deep Learning in Signaling Games for Security and Sustainability (Contributed talk) Elizabeth Bondi
03:30 PM Coffee break (Break)
04:00 PM Invited talk: Asu Ozdaglar (MIT) (Invited talk) Asuman Ozdaglar
04:30 PM Afternoon poster spotlight (Poster spotlight)
Praneeth Netrapalli, Michael Jordan, Nicola Gatti, Alberto Marchesi, Tommaso Bianchi, Sebastian Tschiatschek, Amjad Almahairi, Pascal Vincent, Simon Lacoste-Julien, Moksh Jain, Qihang Lin, Tianbao Yang, Ian Gemp, Dmitry Koralev, Peter Richtarik, Tomi Peltola, Samuel Kaski, Kevin Lai, Andre Wibisono, Youssef Mroueh, Wei Zhang, Xiaodong Cui, Payel Das, Samy Jelassi, Damien Scieur, Arthur Mensch, Joan Bruna, Qiuwei Li, Gongguo Tang, Michael B Wakin, Benjamin Eysenbach, Emilio Parisotto, Eric Xing, Sergey Levine, Ruslan Salakhutdinov, Claire Tomlin, Guodong Zhang, Jimmy Ba, Roger Grosse, devon Hjelm, Aaron Courville, Hengyuan Hu, Jakob Foerster, Noam Brown, Haifeng Xu, Bistra Dilkina, Lillian Ratliff, Shankar Sastry, Benjamin Chasnov, Tanner Fiez, Nathan Kallus, Tobias Schnabel, Christian Kroer, Tuomas Sandholm, Yujia Jin, Aaron Sidford, Kevin Tian, Hongkai Zheng, Anima Anandkumar
05:00 PM Discussion panel (Panel)
05:30 PM Concluding remarks -- afternoon poster session (Poster session)

Author Information

Ioannis Mitliagkas (Mila & University of Montreal)
Gauthier Gidel (Mila)

I am a Ph.D student supervised by Simon Lacoste-Julien, I graduated from ENS Ulm and Université Paris-Saclay. I was a visiting PhD student at Sierra. I also worked for 6 months as a freelance Data Scientist for Monsieur Drive (Acquired by Criteo) and I recently co-founded a startup called Krypto. I'm currently pursuing my PhD at Mila. My work focuses on optimization applied to machine learning. More details can be found in my resume. My research is to develop new optimization algorithms and understand the role of optimization in the learning procedure, in short, learn faster and better. I identify to the field of machine learning (NIPS, ICML, AISTATS and ICLR) and optimization (SIAM OP)

Niao He (UIUC)
Reyhane Askari Hemmat (Mila & University of Montreal)
Nika Haghtalab (Cornell University)
N H (CMU)
Simon Lacoste-Julien (Mila, Université de Montréal)

Simon Lacoste-Julien is a CIFAR fellow and an assistant professor at Mila and DIRO from Université de Montréal. His research interests are machine learning and applied math, with applications in related fields like computer vision and natural language processing. He obtained a B.Sc. in math., physics and computer science from McGill, a PhD in computer science from UC Berkeley and a post-doc from the University of Cambridge. He spent a few years as a research faculty at INRIA and École normale supérieure in Paris before coming back to his roots in Montreal in 2016 to answer the call from Yoshua Bengio in growing the Montreal AI ecosystem.

More from the Same Authors