A Simple yet Universal Strategy for Online Convex Optimization

by   Moshe Y. Vardi, et al.

Recently, several universal methods have been proposed for online convex optimization, and attain minimax rates for multiple types of convex functions simultaneously. However, they need to design and optimize one surrogate loss for each type of functions, which makes it difficult to exploit the structure of the problem and utilize the vast amount of existing algorithms. In this paper, we propose a simple strategy for universal online convex optimization, which avoids these limitations. The key idea is to construct a set of experts to process the original online functions, and deploy a meta-algorithm over the linearized losses to aggregate predictions from experts. Specifically, we choose Adapt-ML-Prod to track the best expert, because it has a second-order bound and can be used to leverage strong convexity and exponential concavity. In this way, we can plug in off-the-shelf online solvers as black-box experts to deliver problem-dependent regret bounds. Furthermore, our strategy inherits the theoretical guarantee of any expert designed for strongly convex functions and exponentially concave functions, up to a double logarithmic factor. For general convex functions, it maintains the minimax optimality and also achieves a small-loss bound.


page 1

page 2

page 3

page 4


Adaptivity and Optimality: A Universal Algorithm for Online Convex Optimization

In this paper, we study adaptive online convex optimization, and aim to ...

Universal Online Optimization in Dynamic Environments via Uniclass Prediction

Recently, several universal methods have been proposed for online convex...

Dual Adaptivity: A Universal Algorithm for Minimizing the Adaptive Regret of Convex Functions

To deal with changing environments, a new performance measure---adaptive...

Universal Online Learning with Gradual Variations: A Multi-layer Online Ensemble Approach

In this paper, we propose an online convex optimization method with two ...

Online Strongly Convex Optimization with Unknown Delays

We investigate the problem of online convex optimization with unknown de...

SAdam: A Variant of Adam for Strongly Convex Functions

The Adam algorithm has become extremely popular for large-scale machine ...

Second-order Quantile Methods for Experts and Combinatorial Games

We aim to design strategies for sequential decision making that adjust t...

Please sign up or login with your details

Forgot password? Click here to reset