Online Convex Optimization with Long Term Constraints for Predictable Sequences

10/30/2022
by   Deepan Muthirayan, et al.
0

In this paper, we investigate the framework of Online Convex Optimization (OCO) for online learning. OCO offers a very powerful online learning framework for many applications. In this context, we study a specific framework of OCO called OCO with long term constraints. Long term constraints are introduced typically as an alternative to reduce the complexity of the projection at every update step in online optimization. While many algorithmic advances have been made towards online optimization with long term constraints, these algorithms typically assume that the sequence of cost functions over a certain T finite steps that determine the cost to the online learner are adversarially generated. In many circumstances, the sequence of cost functions may not be unrelated, and thus predictable from those observed till a point of time. In this paper, we study the setting where the sequences are predictable. We present a novel online optimization algorithm for online optimization with long term constraints that can leverage such predictability. We show that, with a predictor that can supply the gradient information of the next function in the sequence, our algorithm can achieve an overall regret and constraint violation rate that is strictly less than the rate that is achievable without prediction.

READ FULL TEXT
research
04/08/2016

A Low Complexity Algorithm with O(√(T)) Regret and Finite Constraint Violations for Online Convex Optimization with Long Term Constraints

This paper considers online convex optimization over a complicated const...
research
02/19/2018

Online Convex Optimization for Cumulative Constraints

We propose an algorithm for online convex optimization which examines a ...
research
05/02/2023

Projection-Free Online Convex Optimization with Stochastic Constraints

This paper develops projection-free algorithms for online convex optimiz...
research
11/25/2020

Leveraging Predictions in Smoothed Online Convex Optimization via Gradient-based Algorithms

We consider online convex optimization with time-varying stage costs and...
research
04/27/2023

A Best-of-Both-Worlds Algorithm for Constrained MDPs with Long-Term Constraints

We study online learning in episodic constrained Markov decision process...
research
10/21/2019

Robust Online Learning for Resource Allocation – Beyond Euclidean Projection and Dynamic Fit

Online-learning literature has focused on designing algorithms that ensu...
research
08/17/2020

Online Multitask Learning with Long-Term Memory

We introduce a novel online multitask setting. In this setting each task...

Please sign up or login with your details

Forgot password? Click here to reset