DeepAI AI Chat
Log In Sign Up

Online Optimization with Untrusted Predictions

by   Daan Rutten, et al.
Georgia Institute of Technology

We examine the problem of online optimization, where a decision maker must sequentially choose points in a general metric space to minimize the sum of per-round, non-convex hitting costs and the costs of switching decisions between rounds. The decision maker has access to a black-box oracle, such as a machine learning model, that provides untrusted and potentially inaccurate predictions of the optimal decision in each round. The goal of the decision maker is to exploit the predictions if they are accurate, while guaranteeing performance that is not much worse than the hindsight optimal sequence of decisions, even when predictions are inaccurate. We impose the standard assumption that hitting costs are globally α-polyhedral. We propose a novel algorithm, Adaptive Online Switching (AOS), and prove that, for any desired δ > 0, it is (1+2δ)-competitive if predictions are perfect, while also maintaining a uniformly bounded competitive ratio of 2^𝒪̃(1/(αδ)) even when predictions are adversarial. Further, we prove that this trade-off is necessary and nearly optimal in the sense that any deterministic algorithm which is (1+δ)-competitive if predictions are perfect must be at least 2^Ω̃(1/(αδ))-competitive when predictions are inaccurate.


page 1

page 2

page 3

page 4


Online Optimization with Predictions and Non-convex Losses

We study online optimization in a setting where an online learner seeks ...

A New Approach to Capacity Scaling Augmented With Unreliable Machine Learning Predictions

Modern data centers suffer from immense power consumption. The erratic b...

Chasing Convex Bodies and Functions with Black-Box Advice

We consider the problem of convex function chasing with black-box advice...

Beyond Online Balanced Descent: An Optimal Algorithm for Smoothed Online Optimization

We study online convex optimization in a setting where the learner seeks...

The Secretary Problem with Predictions

The value maximization version of the secretary problem is the problem o...

Smoothed Online Optimization for Regression and Control

We consider Online Convex Optimization (OCO) in the setting where the co...

Online Paging with a Vanishing Regret

This paper considers a variant of the online paging problem, where the o...