Safe Linear Bandits over Unknown Polytopes
A Gangrade, T Chen… - The Thirty Seventh Annual …, 2024 - proceedings.mlr.press
The safe linear bandit problem (SLB) is an online approach to linear programming with
unknown objective and unknown\emph {roundwise} constraints, under stochastic bandit …
unknown objective and unknown\emph {roundwise} constraints, under stochastic bandit …
Convex methods for constrained linear bandits
A Afsharrad, A Moradipari, S Lall - 2024 European Control …, 2024 - ieeexplore.ieee.org
Recently, bandit optimization has received significant attention in real-world safety-critical
systems that involve repeated interactions with humans. While there exist various algorithms …
systems that involve repeated interactions with humans. While there exist various algorithms …
A safe first-order method for pricing-based resource allocation in safety-critical networks
B Turan, S Hutchinson… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
We introduce a novel algorithm for solving network utility maximization (NUM) problems that
arise in resource allocation schemes over networks with known safety-critical constraints …
arise in resource allocation schemes over networks with known safety-critical constraints …
Safe dynamic pricing for nonstationary network resource allocation
B Turan, S Hutchinson… - 6th Annual Learning for …, 2024 - proceedings.mlr.press
This paper introduces the Safe Pricing for NUM with Gradual Variations (SPNUM-GV)
algorithm, addressing challenges in pricing-based distributed resource allocation for safety …
algorithm, addressing challenges in pricing-based distributed resource allocation for safety …
Safe and Secure Optimization in Human-Cyber-Physical Systems
B Turan - 2023 - escholarship.org
In our rapidly evolving technological landscape, the proliferation of enabling technologies
for autonomous systems has given rise to a burgeoning realm of societal-scale smart …
for autonomous systems has given rise to a burgeoning realm of societal-scale smart …