5 papers
Recognizing Signomial Convexity is Hard
Rui Zheng, Iosif Sakos, Antonios Varvitsiotis
Signomials---finite sums of generalized monomials with real exponents---are a natural machine learning model, combining parsimonious representations of power laws, inverse relation…
Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback
Anas Barakat, Andreas Kontogiannis, Vasilis Pollatos +2
We study adversarial online learning with hidden-convex losses, i.e., nonconvex losses that become convex after a nonlinear reparameterization. Ghai, Lu and Hazan (2022) proved tha…
Fairness-Guaranteed Online Power Allocation Policies for EV Fast Charging Stations
Can Berk Saner, Yong-Sheng Soh, Antonios Varvitsiotis
The rapid expansion of electric vehicles (EVs) necessitates scalable fast charging station (FCS) infrastructure. These stations are often oversubscribed, with total port rating exc…
When and Why is Optimistic Multiplicative Weights Slow? The Geometry of Energy Dissipation
John Lazarsfeld, Anas Barakat, Georgios Piliouras +2
This paper studies the convergence of the Optimistic Multiplicative Weights Update algorithm (OMWU) in two player zero-sum games. Recent works have identified instances on which th…
Solving Imperfect-Recall Games via Sum-of-Squares Optimization
Rui Zheng, Ryann Sim, Antonios Varvitsiotis
Extensive-form games (EFGs) provide a powerful framework for modeling sequential decision making, capturing strategic interaction under imperfect information, chance events, and te…