Online-Learning for min-max discrete problems

by   Evripidis Bampis, et al.

We study various discrete nonlinear combinatorial optimization problems in an online learning framework. In the first part, we address the question of whether there are negative results showing that getting a vanishing (or even vanishing approximate) regret is computational hard. We provide a general reduction showing that many (min-max) polynomial time solvable problems not only do not have a vanishing regret, but also no vanishing approximation α-regret, for some α (unless NP=BPP). Then, we focus on a particular min-max problem, the min-max version of the vertex cover problem which is solvable in polynomial time in the offline case. The previous reduction proves that there is no (2-ϵ)-regret online algorithm, unless Unique Game is in BPP; we prove a matching upper bound providing an online algorithm based on the online gradient descent method. Then, we turn our attention to online learning algorithms that are based on an offline optimization oracle that, given a set of instances of the problem, is able to compute the optimum static solution. We show that for different nonlinear discrete optimization problems, it is strongly NP-hard to solve the offline optimization oracle, even for problems that can be solved in polynomial time in the static case (e.g. min-max vertex cover, min-max perfect matching, etc.). On the positive side, we present an online algorithm with vanishing regret that is based on the follow the perturbed leader algorithm for a generalized knapsack problem.


page 1

page 2

page 3

page 4


Multi-Receiver Online Bayesian Persuasion

Bayesian persuasion studies how an informed sender should partially disc...

New complexity results and algorithms for min-max-min robust combinatorial optimization

In this work we investigate the min-max-min robust optimization problem ...

Efficient Online Learning of Optimal Rankings: Dimensionality Reduction via Gradient Descent

We consider a natural model of online preference aggregation, where sets...

Efficient Online Learning for Dynamic k-Clustering

We study dynamic clustering problems from the perspective of online lear...

Hierarchies of Relaxations for Online Prediction Problems with Evolving Constraints

We study online prediction where regret of the algorithm is measured aga...

Combinatorial Optimization Problems with Balanced Regret

For decision making under uncertainty, min-max regret has been establish...

Please sign up or login with your details

Forgot password? Click here to reset