Hi! I am a 2nd year PhD student in Industrial Engineering at Purdue University. I am also a member of the Center for AI and Robotic Excellence in medicine, under the guidance of Prof. Juan Wachs. My research is at the intersection of Reinforcement Learning, Stochastic Processes and Computer Vision, with application in healthcare. I am working on diagnosis, prognosis and treatment planning for patients with complex medical conditions, by analysing their ultrasound data. I am also working on one-shot learning in robots for emergency surgery by learning from unsupervised surgical videos. I also have an Integrated Masters of Science in Mathematics and Bachelor of Engineering in Computer Science from BITS Pilani, India, enabling me to work on most theoretical and applied projects in Machine Learning.
Previously, I was a Research Engineering/Scientist Associate at the Oden Institute of Computational Engineering and Sciences at the University of Texas at Austin, as part of my 5th year undergraduate thesis. For knowing more about my academic journey, please refer to my CV or my condensed Resume. Feel free to reach out to me if you want to discuss my work or collaborate on any projects!
Apart from spending my time doing research, I hold a keen interest in music, a passion that I got to pursue as part of the Music Society at BITS, where I gave several performances as a vocalist. I'm grateful to be able to continue to pursue music as part of the Purdue Tagore Society. I am also an avid reader, and very fond of cooking and sketching portraits.
Working on min-time mixing in Annealed Langevin dynamics and Score-based Diffusion models, and extending the sampling updates by using different SDE sequences than plain Brownian motion. Extending the work for rare event estimation.
Developed a factored-STVGP (spatio-temporal variational Gaussian Process) framework for directly mapping any readily available RGB image to hyperspectral. Our model surpassed the current state-of-the-art on hyperspectral imaging benchmarks, thus enabling better classification and object detection.
We developed a generative modeling paradigm called skipGAN which combines GANs and Approximate Bayesian Computing (ABC-GAN), with skip connections. The architecture aims at correcting likelihood misspecification in prior models. Our research demonstrated performance improvements in well-known priors like TabNet, CatBoost, and Stats model for regression tasks across various noisy datasets. Preprint
Implementing the genetic algorithm on various setups of the modular synthesizer, called "organisms". Each organism produces a particular kind of sound. The organisms evolve by undergoing the graph-based processes of mutation and crossover, and natural selection, resulting in changes in connections and setups, evolving from fragments of sound to a section of a musical piece. Process Document, Appendix, Team page
IE 336: Operations Research - Stochastic Models, Purdue University
IE 230: Probability and Statistics for Engineers, Purdue University
CS F213: Discrete Mathematics, BITS Goa
CS F111: Computer Programming, BITS Goa
MATH F243: Graphs and Networks, BITS Goa
Advised a group of juniors on a deeper understanding of generative models, in correspondence with Dr. Snehanshu Saha, BITS Goa.
Mentored and taught over 200 students over multiple colleges in India.
Tutorials and doubt-clearing sessions for first year students in MATH F113, BITS Goa.