Online Metric Algorithms with Untrusted Predictions

Online Optimization with Predictions and Switching Costs: Fast Algorithms and Fundamental Limits

This paper studies an online optimization problem with switching costs and a finite prediction window. We propose a computationally efficient algorithm, Receding Horizon Gradient Descent (RHGD), which only requires a finite number of gradient evaluations at each time. We show that both the dynamic regret and the competitive ratio of the algorithm decay exponentially fast with the length of the ...

Online Algorithms with Advice

Online Algorithms with Advice⋆

In online problems, the input forms a finite sequence of requests. Each request must be processed, i. e., a partial output has to be computed only depending on the requests having arrived so far, and it is not allowed to change this partial output subsequently. The aim of an online algorithm is to produce a sequence of partial outputs that optimizes some global measure. The most frequently used...

Online Learning with an Unknown Fairness Metric

We consider the problem of online learning in the linear contextual bandits setting, but in which there are also strong individual fairness constraints governed by an unknown similarity metric. These constraints demand that we select similar actions or individuals with approximately equal probability [Dwork et al., 2012], which may be at odds with optimizing reward, thus modeling settings where...

Online Convex Optimization Using Predictions

Making use of predictions is a crucial, but under-explored, area of online algorithms. This paper studies a class of online optimization problems where we have external noisy predictions available. We propose a stochastic prediction error model that generalizes prior models in the learning and stochastic control communities, incorporates correlation among prediction errors, and captures the fac...