Parameter-free Online Linear Optimization with Side Information via Universal Coin Betting

by   J. Jon Ryu, et al.

A class of parameter-free online linear optimization algorithms is proposed that harnesses the structure of an adversarial sequence by adapting to some side information. These algorithms combine the reduction technique of Orabona and Pál (2016) for adapting coin betting algorithms for online linear optimization with universal compression techniques in information theory for incorporating sequential side information to coin betting. Concrete examples are studied in which the side information has a tree structure and consists of quantized values of the previous symbols of the adversarial sequence, including fixed-order and variable-order Markov cases. By modifying the context-tree weighting technique of Willems, Shtarkov, and Tjalkens (1995), the proposed algorithm is further refined to achieve the best performance over all adaptive algorithms with tree-structured side information of a given maximum order in a computationally efficient manner.


page 1

page 2

page 3

page 4


A Comprehensive Approach to Universal Piecewise Nonlinear Regression Based on Trees

In this paper, we investigate adaptive nonlinear regression and introduc...

Best of many worlds: Robust model selection for online supervised learning

We introduce algorithms for online, full-information prediction that are...

Fixed-Parameter Algorithms for Longest Heapable Subsequence and Maximum Binary Tree

A heapable sequence is a sequence of numbers that can be arranged in a "...

Parameter-free Mirror Descent

We develop a modified online mirror descent framework that is suitable f...

In a Nutshell: Sequential Parameter Optimization

The performance of optimization algorithms relies crucially on their par...

Partition Tree Weighting

This paper introduces the Partition Tree Weighting technique, an efficie...

Please sign up or login with your details

Forgot password? Click here to reset