Clik here to view.
Mathematical Analysis of Policy Gradient Methods
Most papers using reinforcement learning these days use the policy gradient class of learning. In this post, I will cover a basic tutorial of policy gradient, uncover some confusion on using baseline...
View ArticleClik here to view.
Writing and Proofreading Research Code
Most papers in Artificial Intelligence (AI) research these days have an accompanying source code. Sometimes authors will release their code with their paper after publication (our research group always...
View ArticleClik here to view.
Are we doing NLP the right way?
I have been pondering over some of these questions below for sometime and after taking a break from chasing many paper deadlines, I found sometime over Christmas to pen down my thoughts. I’ll discuss...
View ArticleClik here to view.
Are Synthetic Datasets in AI Useful?
Problems in Artificial Intelligence (AI) are generally approached by solving a dataset/setup that is a proxy of the real world. This is a fairly old practice going back to the start of AI as a field....
View ArticleClik here to view.
Mathursday: Dynkin’s π-λ Theorem and CDF (Part 1)
I am starting a new series of posts called “Mathursday” (portmanteau: Maths+Thursday) containing short articles on important mathematical results. Today’s article is about Dynkin’s π-λ Theorem and...
View ArticleClik here to view.
Mathursday: Dynkin’s π-λ Theorem and CDF (Part 2)
The aim of this post is to prove that a cummulative distribution function (CDF) uniquely determines the probability distribution. This is a well known fundamental result that is quite intuitive but...
View ArticleGrowing Bifurcation of AI Scholarship
The field of artificial intelligence (which includes machine learning, computer vision, natural language understanding etc.) is going through an unprecedented phase of interest and enthusiasm. This is...
View ArticleClik here to view.
Mathursday: PAC with Hoeffding-Bernstein
PAC results with Hoeffding-Bernstein’s inequality are the bread and butter of machine learning theory. In this post, we’ll see how to use Hoeffding’s inequality to derive agnostic PAC bounds with an...
View ArticleAcademia and Compute-Intensive AI Research
Artificial Intelligence research (AI) has achieved great empirical success in the last decade. One major reason has been the availability of fast GPU and CPU clusters that have made it possible to run...
View ArticleClik here to view.
Mathursday: Rayleigh-Ritz, Courant-Fischer, and Weyl’s Inequality
Mathursday is back after a very long time. The last year was unusually hectic for all of us and I couldn’t devote enough time to posts. We restart with the study of eigenvalues which finds significant...
View Article