A Tutorial on Online Supervised Learning with Applications to Node Classification in Social Networks

08/31/2016
by   Alexander Rakhlin, et al.
0

We revisit the elegant observation of T. Cover '65 which, perhaps, is not as well-known to the broader community as it should be. The first goal of the tutorial is to explain---through the prism of this elementary result---how to solve certain sequence prediction problems by modeling sets of solutions rather than the unknown data-generating mechanism. We extend Cover's observation in several directions and focus on computational aspects of the proposed algorithms. The applicability of the methods is illustrated on several examples, including node classification in a network. The second aim of this tutorial is to demonstrate the following phenomenon: it is possible to predict as well as a combinatorial "benchmark" for which we have a certain multiplicative approximation algorithm, even if the exact computation of the benchmark given all the data is NP-hard. The proposed prediction methods, therefore, circumvent some of the computational difficulties associated with finding the best model given the data. These difficulties arise rather quickly when one attempts to develop a probabilistic model for graph-based or other problems with a combinatorial structure.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/26/2020

Graph Embedding for Combinatorial Optimization: A Survey

Graphs have been widely used to represent complex data in many applicati...
research
04/02/2022

Improved Approximation Algorithm for Graph Burning on Trees

Given a graph G=(V,E), the problem of is to find a sequence of nodes fr...
research
03/04/2015

Hierarchies of Relaxations for Online Prediction Problems with Evolving Constraints

We study online prediction where regret of the algorithm is measured aga...
research
04/01/2021

The k-Colorable Unit Disk Cover Problem

In this article, we consider colorable variations of the Unit Disk Cover...
research
05/27/2021

An Impossibility Theorem for Node Embedding

With the increasing popularity of graph-based methods for dimensionality...
research
03/29/2020

A combinatorial MA-complete problem

Despite the interest in the complexity class MA, the randomized analog o...
research
10/09/2019

Unaligned Image-to-Sequence Transformation with Loop Consistency

We tackle the problem of modeling sequential visual phenomena. Given exa...

Please sign up or login with your details

Forgot password? Click here to reset