1 citations · 1 across the 5 of their papers we have counts for
6 papers
Gradient-Only Online Convex Optimization with a Single Quadratic Leader
Kamiar Asgari
We study online convex optimization on a bounded Euclidean domain when the learner receives only one subgradient at its prediction and knows neither the horizon, a gradient bound,…
Optimal Regret for Online Storage Control via Cumulative Policies
Kamiar Asgari, Michael J. Neely
We study online control of a scalar storage system with adversarial nonnegative arrivals, known retention coefficient, and convex costs depending on both state and action. Each act…
Online Constrained Control of Storage Systems via Simplex Disturbance-Action Policies
Kamiar Asgari, Michael J. Neely
We study online control of a scalar storage system with nonnegative adversarial resource arrivals and state-dependent action constraints. The adversarial, time-varying cost depends…
Bandit-Based Rate Adaptation for a Single-Server Queue
Mevan Wijewardena, Kamiar Asgari, Michael J. Neely
This paper considers the problem of obtaining bounded time-average expected queue sizes in a single-queue system with a partial-feedback structure. Time is slotted; in slot the…
Nonsmooth Projection-Free Optimization with Functional Constraints
Kamiar Asgari, Michael J. Neely
This paper presents a subgradient-based algorithm for constrained nonsmooth convex optimization that does not require projections onto the feasible set. While the well-established…
Projection-Free Non-Smooth Convex Programming
Kamiar Asgari, Michael J. Neely
We study nonsmooth convex minimization over a compact convex set without projections. For a globally -Lipschitz objective, optimistic primal-dual updates give error at most $2LD…