11 papers
Rate-Optimal Regret for the Safe Learning-based Control of the Constrained Linear Quadratic Regulator
Spencer Hutchinson, Nanfei Jiang, Mahnoosh Alizadeh
We study the problem of adaptive control of the stochastic linear quadratic regulator (LQR) with constraints that must be satisfied at every time step. Prior work on the multidimen…
Steady-state Based Approach to Online Non-stochastic Control
Vijeth Hebbar, Spencer Hutchinson, Mahnoosh Alizadeh +1
We study the problem of online non-stochastic control (ONC), which is the control of a linear system under adversarial disturbances and adversarial cost functions, with the aim of…
The Safety-Privacy Tradeoff in Linear Bandits
Arghavan Zibaie, Spencer Hutchinson, Ramtin Pedarsani +1
We consider a collection of linear stochastic bandit problems, each modeling the random response of different agents to proposed interventions, coupled together by a global safety…
Constrained Online Convex Optimization with Polyak Feasibility Steps
Spencer Hutchinson, Mahnoosh Alizadeh
In this work, we study online convex optimization with a fixed constraint function . Prior work on this problem has shown reg…
Online Nonstochastic Control with Convex Safety Constraints
Nanfei Jiang, Spencer Hutchinson, Mahnoosh Alizadeh
This paper considers the online nonstochastic control problem of a linear time-invariant system under convex state and input constraints that need to be satisfied at all times. We…
Safe Online Convex Optimization with Multi-Point Feedback
Spencer Hutchinson, Mahnoosh Alizadeh
Motivated by the stringent safety requirements that are often present in real-world applications, we study a safe online convex optimization setting where the player needs to simul…
Optimistic Safety for Online Convex Optimization with Unknown Linear Constraints
Spencer Hutchinson, Tianyi Chen, Mahnoosh Alizadeh
We study the problem of online convex optimization (OCO) under unknown linear constraints that are either static, or stochastically time-varying. For this problem, we introduce an…
A Safe First-Order Method for Pricing-Based Resource Allocation in Safety-Critical Networks
Berkay Turan, Spencer Hutchinson, Mahnoosh Alizadeh
We introduce a novel algorithm for solving network utility maximization (NUM) problems that arise in resource allocation schemes over networks with known safety-critical constraint…
Directional Optimism for Safe Linear Bandits
Spencer Hutchinson, Berkay Turan, Mahnoosh Alizadeh
The safe linear bandit problem is a version of the classical stochastic linear bandit problem where the learner's actions must satisfy an uncertain constraint at all rounds. Due it…
Safe Pricing Mechanisms for Distributed Resource Allocation with Bandit Feedback
Spencer Hutchinson, Berkay Turan, Mahnoosh Alizadeh
In societal-scale infrastructures, such as electric grids or transportation networks, pricing mechanisms are often used as a way to shape users' demand in order to lower operating…
The Impact of the Geometric Properties of the Constraint Set in Safe Optimization with Bandit Feedback
Spencer Hutchinson, Berkay Turan, Mahnoosh Alizadeh
We consider a safe optimization problem with bandit feedback in which an agent sequentially chooses actions and observes responses from the environment, with the goal of maximizing…