Masters in Machine Learning
Carnegie Mellon University (alalan at cs dot cmu dot edu)
arshika77 at gmail dot com


Machine Learning Theory and Applications Research

Bio

I am a Master of Science student in Machine Learning at Carnegie Mellon University, where I am learning to conduct specialized theoretical and applied machine learning research through PhD-level coursework.

Previously, I worked as a predoctoral researcher at Google DeepMind (formerly Google Research India), focusing on developing robust reinforcement learning algorithms to build a policy for efficiently delivering health awareness information in underserved communities in India.

Before that, I was a Research Assistant at the Kreiman Lab at Harvard University, where I worked on adopting continual learning algorithms for continuous domain adaptation.

My research interests lie in building and refining theoretical approaches to machine learning challenges in generative AI, reinforcement learning, and language models. I aim to contribute to the development of robust and adaptive AI systems that can effectively sense, interact with, and adapt to dynamic environments.

My resume is available here.

BITS Pilani
2017 - 2022
Harvard University
2021-2022
Google DeepMind
2022 - 2024
Carnegie Mellon University
2024 - present

I graduated from Birla Institute of Technology and Science (BITS), Pilani in 2022. I enjoy writing as a medium of creative expression and you can find some of my works here, here and here. I also am a avid reader, you can find my reading list here.

Updates

  • [Aug 2024] Joined Carnegie Mellon University as a masters student in the Machine Learning Department!
  • [Feb 24] Our work on Improving Health Information Access in the World’s Largest Maternal Mobile Health Program via Bandit Algorithms was accepted at the Innovative Applications of Artificial Intelligence 2024 was presented as an Oral Presentation at AAAI
  • [May 23] Our preliminary work on Analyzing and Predicting Low-Listenership Trends in a Large-Scale Mobile Health Program was accepted at the Data Science for Social Good Workshop, KDD 2023 as an Oral Presentation
  • [Dec 22] Our work on Adherence Bandits, a specialized RMAB subclass designed to address the complexities of adherence within the domain of public health got accepted at the Artificial Intelligence for Social Good Workshop, AAAI 2023
  • [Aug 22] Joined Google AI India as Pre-Doctoral Reseacher! Working with Milind Tambe within MASSI.
  • [Aug 21] Joined the Kreiman Lab at Harvard University!
  • [Oct 21] Our work on ** a biologically inspired an SNN-based SDM utilizing N-of-M encoding** was aceepted at the Bernstein Conference 2021.
  • [Aug 20] Accepted to CBMM’s Brain, Minds and Machines Summer School!

Publications

Improving Health Information Access in the World’s Largest Maternal Mobile Health Program via Bandit Algorithms

A Lalan*, S Verma*, P Diaz, P Danassis, A Mahale, K Sudan, A Hegde, M Tambe, A Taneja
Oral Presentation @ Innovative Applications of Artificial Intelligence (IAAI 2024) Paper

Analyzing and Predicting Low-Listenership Trends in a Large-Scale Mobile Health Program: A Preliminary Investigation

A Lalan, S Verma, K Sudan, A Mahale, A Hegde, M Tambe, A Taneja
Oral Presentation @ Data Science for Social Good Workshop, KDD 2023 Paper

Adherence Bandits

J Killian*, A Lalan*, A Mate*, M Jain, A Taneja, M Tambe
Artificial Intelligence for Social Good Workshop, AAAI 2023 Paper

Continual Learning and Out of Domain Generalization in Continuous Domain Adaptation

A Lalan, S Mandan, M Zhang, G Kreiman
Undergraduate Thesis 2022 Paper

Sparse Distributed Memory Using Spiking Neural Networks on Nengo

R Ajwani, A Lalan, B Bhattacharya, J Bose
Bernstein Conference 2021 Paper

Epigraphiology: A Hybrid Approach for Measuring and Analyzing Influence Diffusion in Article Networks

S Dey, S Kotian, S Saha, A Agarwal, A Lalan, G Sampatrao
Journal of Scientometric Research Paper