7 papers
Near-Optimal Private Tests for Simple and MLR Hypotheses
Yu-Wei Chen, Raghu Pasupathy, Jordan Awan
We develop a near-optimal testing procedure under the framework of Gaussian differential privacy for simple as well as one- and two-sided tests under monotone likelihood ratio cond…
Deterministic and Stochastic Frank-Wolfe Recursion on Probability Spaces
Di Yu, Shane G. Henderson, Raghu Pasupathy
Motivated by applications in emergency response and experimental design, we consider smooth stochastic optimization problems over probability measures supported on compact subsets…
Frank-Wolfe Recursions for the Emergency Response Problem on Measure Spaces
Di Yu, Shane G. Henderson, Raghu Pasupathy
We consider an optimization problem over measures for emergency response to out-of-hospital cardiac arrest (OHCA), where the goal is to allocate volunteer resources across a spatia…
Drift Optimization of Regulated Stochastic Models Using Sample Average Approximation
Zihe Zhou, Harsha Honnappa, Raghu Pasupathy
This paper introduces a drift optimization model of stochastic optimization problems driven by regulated stochastic processes. A broad range of problems across operations research,…
On The Global Convergence Of Online RLHF With Neural Parametrization
Mudit Gaur, Amrit Singh Bedi, Raghu Pasupathy +1
The importance of Reinforcement Learning from Human Feedback (RLHF) in aligning large language models (LLMs) with human values cannot be overstated. RLHF is a three-stage process t…
Complexity of Zeroth- and First-order Stochastic Trust-Region Algorithms
Yunsoo Ha, Sara Shashaani, Raghu Pasupathy
Model update (MU) and candidate evaluation (CE) are classical steps incorporated inside many stochastic trust-region (TR) algorithms. The sampling effort exerted within these steps…