Second Order Regret Bounds Parametrized By Variance Across Actions And Top Epsilon Percentile

Second order regret bounds parametrized by variance across actions and top percentile This blog will describe an open problem posted by Yoav Freund[1]. We’ll introduce the problem setting and an overview of regret bounds in section 1. In section 2, we’ll define variance across actions and how it comes into play. Then we’ll introduce percentile… Continue reading Second Order Regret Bounds Parametrized By Variance Across Actions And Top Epsilon Percentile

Efficiently Learning Ising Models on Arbitrary Graphs [STOC’15]

The paper [1] presented in this blog is from Professor Guy Bresler at Massachusetts Institute of Technology. It was originally presented at the 47th Annual Symposium on the Theory of Computing (STOC, 2015). The paper mainly talks about how to reconstruct a graph with an Ising model given i.i.d data samples. Without any restrictive constraints… Continue reading Efficiently Learning Ising Models on Arbitrary Graphs [STOC’15]

Restricted Boltzmann Machines for Collaborative Filtering

0. Gentle Description of RBMs Restricted Boltzmann Machines (RBM) are neural networks consisting of stochastic binary nodes that are utilized to learn the ‘connection’ between a layer of observed nodes and a layer of latent nodes. The ‘restricted’ property refers to the fact that every node is unconnected to every other node within the same… Continue reading Restricted Boltzmann Machines for Collaborative Filtering

Towards theoretical understanding of Domain Adaptation Learning

1. Introduction Machine Learning (ML) is used in many real world applications thanks to its powerful theory that has led to a wide variety of highly successful practical tools. However, the main problem with the theory is that it makes simple unrealistic assumptions that clearly fail in many real world applications. More specifically, a basic… Continue reading Towards theoretical understanding of Domain Adaptation Learning