Anirudh's Blog on Anirudh Vemula

Day 2 of doing advent of code using Racket.

I’ve been meaning to revisit Racket for a very long time.

In my previous post, we discussed a neat intuition for nonparametric density estimation and introduced a nonparametric method, histograms.

Parametric density estimation, a.k.a fitting probability distribution to observed data by tweaking the parameters of the distribution’s functional form, is all the rage now with generative modeling and LLMs.

We will continue with part 3 (and the final part) of the blog post series on this book by Bertsekas.

This is part 2 of the blog post series on this book from Bertsekas, and its key takeaways.

I recently came across this book from Bertsekas that looked very interesting.

Francesco Orabona’s monograph on online learning has a very neat and intuitive way of looking at AdaGrad.

In this blog post, I will summarize the key contributions of my recent submission on CMAX++.

$K$ arms, $T$ rounds (assume known $K$ and $T$) Goal is to maximize total reward over $T$ rounds Assumptions Bandit Feedback: only observe reward for the arm played IID rewards: For each arm $a$, $\exists$ a reward distribution $D_a$ which is unknown Per-…

The framework of OCO with memory is: At each round $t$, player chooses $x_t \in K \subset \mathbb{R}^n$ Then, a loss $f_t: K^{m+1} \rightarrow \mathbb{R}$ is revealed and player suffers loss of $f_t(x_{t-m}, \cdots, x_t)$ Assume $0 \in K$, and $f_t(x_0, \…

Exp-concave Functions OGD achieves logarithmic regret for strongly convex and lipschitz functions (see this note), but this is a rather strong condition.

Turns out we can do better $\sqrt{T}$ regret we saw for OGD analysis for convex lipschitz losses if they possess some curvature that can be exploited.

Similar to SGD but different: loss functions are different at each time step Algorithm Projected Online Gradient Descent: $x_1 \in V \subseteq \mathbb{R}^d$ where $V$ is a closed, convex set and $\eta_1, \cdots, \eta_T > 0$ for $t = 1, \cdots, T$ Play $x_…

An alternative approach to projected gradient descent for minimizing a smooth convex function $f$ over a compact, convex set $K$.

KL-divergence is given by: $$ D_{KL}(P||Q) = \mathbb{E}_{x \sim P}\left[\log \frac{P(X)}{Q(X)}\right] $$ It is not necessarily symmetric, so $D_{KL}(P||Q) \neq D_{KL}(Q||P)$, thus it cannot be used as a distance metric.

Several years ago, I came across this letter written by Hunter S.

Very recently, I submitted a paper to RSS (update: accepted!)

Thoughts on the conference My overall impression of AISTATS was that its a really good conference if statistical ML is what you are interested/working in.

Some of these photos were taken in New York city when I visited it in October for an AI forum.

Early fall 2017, I went on a search for graffiti in Pittsburgh and found a lot!