Soumyajit Gupta
PhD Student (In Candidacy)
Department of Computer Science
University of Texas at Austin
smjtgupta@utexas.edu
Interest: Machine Learning, Deep Learning, Fairness, Bioinformatics, Image Processing and Natural Language Processing
I am a PhD student (in Candidacy since Nov 2023) in Department of Computer Science at
the University of Texas at Austin.
I am co-advised by Matthew Lease and
Maria De-Arteaga towards my dissertation
on Multi-Task Learning for group-targeted tasks.
I am a member of the Artificial Intelligence and Human-Centered Computing (AI&HCC) Lab.
From 2014 - 2018 I worked on structural and spectral processing for Cancer Detection
from Hyperspectral Images
under Chadrajit Bajaj.
I hold dual Masters degree: MS in Computer Science from UT Austin and MTech in Image Processing and Vision (EE)
from IIT Kharagpur, under Jayanta Mukhopadhyay and Ritwik Layek on Computational models for Image Saliency.
High-Precision, Low-weight, Fully Interpretable, Neural SVD solver for Big Data
A two stage neural optimization approach as an alternative to conventional and randomized SVD techniques, where the memory requirement depends explicitly on the feature dimension and desired rank, independent of the sample size. The network minimization problem converges to a low rank approximation with high precision. Our architecture is fully interpretable where all the network outputs and weights have a specific meaning.
A Two-Stage Neural Framework for Non-Convex and Discontinuous Pareto Front Approximation.
A low cost, two-stage, hybrid neural Pareto optimization approach is accurate and scales with data dimensions,and number of functions and constraints. The neural network efficiently extracts a weak Pareto front, using Fritz-John conditions as the discriminator. The second stage is a low-cost, Pareto filter to extract the strong Pareto optimal subset. Fritz-John conditions provide us with theoretical bounds on approximation error.
Research and Other Updates