{:refdef: style="text-align: center;"} {:width="250px"} {: refdef}

Welcome to my homepage! I am a passionate problem solver, and I also love to write code. You can find a lot of what I do on this site.

As part of the Laboratory for Computational Social Systems (LCS2) @IIT Delhi{:target="_blank"} (led by Dr. Tanmoy Chakraborty{:target="_blank"}) as a research assistant, I'm currently working on problems revolving around large language models (LLMs), particularly problems on model and inference efficiency, and fact-discovery capabilities of LLMs.

During my masters (@CMI{:target="_blank"}), I also worked as a research assistant at the Networks and Learning Group at TIFR Mumbai{:target="_blank"} (led by Dr. Abhishek Sinha{:target="_blank"}), wherein I worked on problems in the intersection of learning theory, convex optimization and online algorithms. This work involved designing provably optimal online policies for many problems arising frequently in ML domains: the online subset selection problem, for which we introduced an efficient online policy (which is also the first of it's kind to incorporate hints in learning optimal subsets), the contextual bandits problem with a new concave $\alpha$-fairness objective, for which we developed the first such policy in the bandit information setup, and problems in the domain of online meta-learning and multi-task learning. Check out my research work{:target="_blank"}.

I'm also interested in applied areas of ML, including deep learning, natural language processing (particularly LLMs) and automatic differentation (in particular, source to source AD. Art like Zygote.jl{:target="_blank"}). I also like to learn about programming languages and the ecosystem of toolchains surrounding them. In math, I'm mainly interested in algebra, topology and probability theory.

In my free time, I love contributing to and exploring open source software, and write about OSS and linux. Check out some of my open source contributions on my GitHub profile(@codetalker7){:target="_blank"} or here{:target="_blank"}. I've also described my configuration{:target="_blank"} and written some blogs on various topics (including OSS, set-ups and linux; you can see them on the navigation pane on the left). I also love speed typing (this{:target="_blank"} is my last TypeRacer profile, which I've abandoned. I'm currently using this{:target="_blank"} one). I'm also a huge NBA fan, and I love listening to and playing metal music (one of my favorite bands is Periphery{:target="_blank"})!

This website is updated whenever I have something new to add (check the bottom of this page for major updates). My contact information is available below. I would love to talk about math/computer science/open source software. A copy of my resume is available on request.

• Email: [email protected], [email protected].
• Google Scholar: Siddhant Chaudhary
• Discord: Siddhant Chaudhary#8409.
• LinkedIn: Siddhant Chaudhary{:target="_blank"}.
• Twitter: Siddhant Chaudhary
• Keybase: Siddhant Chaudhary{:target="_blank"}.

About this website

This webpage was made using Jekyll's Gitbook{:target="_blank"} theme. I was using my own template in the old website, which I had been wanting to change for a while. The old website still lives in the main branch of the codetalker7.github.io repository. {: .block-tip }

• [06/2024]  Our paper{:target="_blank"} on fair contextual bandits accepted at FoRLaC@ICML2024{:target="_blank"}!

• [05/2024]  Joined LCS2@IITD{:target="_blank"} as an RA!

• [05/2024]  Accepted as a Google Summer of Code 2024 contributor{:target="_blank"} (my second time doing GSoC)! Will be working on a GenAI project{:target="_blank"} for The Julia Language{:target="_blank"}.

• [10/2023]  Our paper{:target="_blank"} on fair contextual bandits is out.

• [02/2023]  Our paper{:target="_blank"} on the online subset selection problem is out.