welcome. i'm a masters student in machine learning at Carnegie Mellon.
i like computing. i really like computing that approximates the complex real-world. here is my curriculum vitae.
let's get to know each other. please scroll down, or use the navbar above.
on mobile? got motion sickness? prefer retro? try the static version of the website .
I’m an MS student at the MLD at SCS, CMU. I've joined Prof. Pradeep Ravikumar's group. These days, I mostly work on representation learning. My overarching agenda is to discover learning paradigms that are democratic & usable in some sense. C’est moi.
I try to develop mathematical and computational tools with the goal of disentangling aleatoric natural variation from the epistemic universal truths that ground it. I think there is much to exploit from higher-order interactions between variables that are atomic to a model, even after we accept any symbolic truths beneath its granularity as aleatoric uncertainty. Recently, I have been working on some exciting problems at the intersection of variational inference, experimental design, generative models and SSL.
Besides machine learning, my background also includes some systems (I particularly enjoy aspects related to security and performance modelling), communication theory and robotics. I recently graduated from IIT Kharagpur. After 5 years of pain, I got a B.Tech in ECE and M.Tech in Vision & Intelligent Systems (from the E&ECE department), and a minor in CS (from the CS&E department). There, I got my start working on robot perception with the AGV research group supervised by Prof. Debashish Chakravarty. The post-CoViD funding winter sowed the seeds of my pursuit of democratic and usable ML.
Supported by an NSF REU, I worked on greedy and distributed learning with Prof. David Inouye at Purdue, which is a direction I brought back to AGV. Enabled by support from Boeing and the IITKGP Foundation USA, I worked on Amelia at CMU SCS’ RI, writing fast map-matching algorithms and hacking away at LLM-logic feedback loops. For my 5th year M.Tech project I worked with Prof. Saumik Bhattacharya on probabilistic symbolic representations and conformal prediction.
In my free time, I enjoy playing and watching sports (especially basketball). I helped IIT KGP bag gold at an inter-IIT tech meet (indoor drone nav) and 2 cultural meets (word games and the likes). I also hope to get back into competitive programming (though I've only formally participated in one competition-- when I was in HS) and CTFs (inspired by Prof. Mainack Mondal’s brilliant infosec course). Though I was born in Baltimore, I grew up in the wonderful Hauz Khas, New Delhi, India; I visit as often as I can.
I'll update this section as I take up projects in grad school. If you are interested in my earlier work (mostly on MLSys and robot perception), please consult my Google Scholar profile.
For smaller and not yet-published projects, click here.
For samples of my code, check out my GitHub profile. It doesn't have the best of my work (let alone all of it), but there's something. As things have turned out, Python is the lingua franca of the ML community, so I've been writing a lot of Python since ~2020. Of late, I've also been trying to integrate C++, and (more interestingly) Haskell in my intermediate and backend code. There is so much data manipulation that bootstraps most research ML code. There, faster computation and type safety is a boon.
My e-mail is aviamala@iitkgp.andrew.co.cmu..comedu. I anticipate your hate mail.
My email and LinkedIn are probably the easiest way to get a hold of me.
I also have a Twitter (avi_amalanshu) but I don't really use it.
Check out my blog: malansh on Medium.
I'm always on the lookout for interesting puzzles and research problems, especially stuff that's interdisciplinary or niche (underappreciated). Let's talk if you have something interesting and can use my contributions.
I enjoy dispensing advice and mentorship (to the extent that I often do so unsolicited). So feel free to solicit if you're interested! Folks who have taken my advice are doing great and those who've ignored it are invariably suffering.