10 papers
The Cost of Learning Under Multiple Change Points
Tomer Gafni, Garud Iyengar, Assaf Zeevi
We consider an online learning problem in environments with multiple change points. In contrast to the single change point problem that is widely studied using classical "high conf…
Variance-Adaptive Optimal Algorithm for Reinforcement Learning with Multinomial Logit Function Approximation
Wonyoung Kim, Min-Hwan Oh, Garud Iyengar +1
Reinforcement learning with multinomial logistic (MNL) function approximation has become an important framework due to its flexibility and broad applicability. While existing studi…
Model-Free Assessment of Simulator Fidelity via Quantile Curves
Garud Iyengar, Yu-Shiou Willy Lin, Kaizheng Wang
As generative AI models are increasingly used to simulate real-world systems, quantifying the ``sim-to-real'' gap is critical. For each input setting of interest -- which we call a…
On the Convergence of Alternating Gradient Descent-Ascent in Bilinear Games
Tianlong Nan, Shuvomoy Das Gupta, Garud Iyengar +1
We study the alternating gradient descent-ascent (AltGDA) algorithm in two-player zero-sum games. Alternating methods, where players take turns to update their strategies, have lon…
Linear Bandits with Partially Observable Features
Wonyoung Kim, Sungwoo Park, Garud Iyengar +2
We study the linear bandit problem that accounts for partially observable features. Without proper handling, unobserved features can lead to linear regret in the decision horizon $…
Virtual Trading in Multi-Settlement Electricity Markets
Agostino Capponi, Garud Iyengar, Bo Yang +1
In the Day-Ahead (DA) market, suppliers sell and load-serving entities (LSEs) purchase energy commitments, with both sides adjusting for imbalances between contracted and actual de…