Optimal Tracking in Prediction with Expert Advice

by   Hakan Gokcesu, et al.

We study the prediction with expert advice setting, where the aim is to produce a decision by combining the decisions generated by a set of experts, e.g., independently running algorithms. We achieve the min-max optimal dynamic regret under the prediction with expert advice setting, i.e., we can compete against time-varying (not necessarily fixed) combinations of expert decisions in an optimal manner. Our end-algorithm is truly online with no prior information, such as the time horizon or loss ranges, which are commonly used by different algorithms in the literature. Both our regret guarantees and the min-max lower bounds are derived with the general consideration that the expert losses can have time-varying properties and are possibly unbounded. Our algorithm can be adapted for restrictive scenarios regarding both loss feedback and decision making. Our guarantees are universal, i.e., our end-algorithm can provide regret guarantee against any competitor sequence in a min-max optimal manner with logarithmic complexity. Note that, to our knowledge, for the prediction with expert advice problem, our algorithms are the first to produce such universally optimal, adaptive and truly online guarantees with no prior knowledge.


page 1

page 2

page 3

page 4


Second Order Regret Bounds Against Generalized Expert Sequences under Partial Bandit Feedback

We study the problem of expert advice under partial bandit feedback sett...

Constant regret for sequence prediction with limited advice

We investigate the problem of cumulative regret minimization for individ...

A Generalized Online Algorithm for Translation and Scale Invariant Prediction with Expert Advice

In this work, we aim to create a completely online algorithmic framework...

Efficient and Optimal Fixed-Time Regret with Two Experts

Prediction with expert advice is a foundational problem in online learni...

Adversarial Policies in Learning Systems with Malicious Experts

We consider a learning system based on the conventional multiplicative w...

Coupling Online-Offline Learning for Multi-distributional Data Streams

The distributions of real-life data streams are usually nonstationary, w...

Please sign up or login with your details

Forgot password? Click here to reset