Convex-Concave Min-Max Stackelberg Games
Dec 6, 2021
Speakers
Denizalp Goktas
Speaker · 0 followers
About
Min-max optimization problems (i.e., games) are attracting a great deal of attention because of their applicability to a wide range of machine learning problems. Although significant progress has been made recently, the literature to date has focused on games with independent strategy sets; little is known about solving games with dependent strategy sets. We introduce a first-order method that solves a large class of convex-concave min-max games with dependent strategy sets, and show that our method converges in polynomial time. To illustrate the importance of solving min-max games with dependent strategy sets, we observe that the computation of competitive equilibria in Fisher markets is an instance of this model. Further, we demonstrate the efficacy and efficiency of our algorithms in practice by computing competitive equilibria in Fisher markets with varying utility structures. Our experiments suggest potential ways to extend our theoretical results, by demonstrating how different smoothness properties can affect the convergence rate of our algorithms.Min-max optimization problems (i.e., games) are attracting a great deal of attention because of their applicability to a wide range of machine learning problems. Although significant progress has been made recently, the literature to date has focused on games with independent strategy sets; little is known about solving games with dependent strategy sets. We introduce a first-order method that solves a large class of convex-concave min-max games with dependent strategy sets, and show that our me…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Adaptable Agent Populations via a Generative Model of Policies
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Non-Gaussian Gaussian Processes for Few-Shot Regression
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Re-labeling Domains Improves Multi-Domain Generalization
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Learning Meaningful Representations of Cells in Microscopy Images
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Optimal Sketching for Trace Estimation
Watch later
Shuli Jiang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%