Squint provides a codebase to perform numerical proof-of-concept experiments in learning theory, particularly in Prediction with Expert Advice problems, a core problem in learning theory.
The software has been developed in the Machine Learning group and is a companion to the research paper 'Second-order Quantile Methods for Experts and Combinatorial Games'. The algorithm is provably robust, was designed to be highly adaptive, and performs excellently in a broad spectrum of practical environments.
The MetaGrad algorithm can be regarded as a successor to Squint, in the sense that it applies to a more general problem, i.e. Online Convex Optimization.
|Safe Statistics , Machine Learning at the Intrinsic Task Pace|
This repository contains a numerically stable implementation of the Squint algorithm from the paper
Second-Order Quantile Methods for Experts and Combinatorial Games Koolen, Wouter M., and Tim van Erven In Proceedings of the 28th Annual Conference on Learning Theory (COLT) 2015, 1155–75
|Organisation||Algorithms and Complexity|
Koolen-Wijkstra, W.M. (2015). Squint.
|view at Bitbucket|