Hi, I’m Sarath, a PhD student in Ming Hsieh Department of Electrical and Computer Engineering at University of Southern California. My research advisor is Prof. Antonio Ortega.

I’m broadly interested in graphs and machine learning. Currently, I focus on non parametric, neighborhood algorithms for understanding data and deep learning models.

What’s New

[July 2021] Model selection and explainability in neural networks using a polytope interpolation framework accepted at Asilomar 2021

[Jan 2021] Revisiting local neighborhood methods in machine learning accepted at DSLW 2021

[Oct 2020] Efficient graph construction for image representation wins Best Student Paper Award at ICIP2020.

[Aug 2020] Graph based deep learning analysis and instance selection with Keisuke accepted at MMSP 2020

[July 2020] Paper on arxiv: DeepNNK: Explaining deep models and their generalization using polytope interpolation

[May 2020] Efficient graph construction for image representation accepted at ICIP 2020

[Feb 2020] Graph Construction from Data by Non-Negative Kernel Regression accpeted at ICASSP 2020


Prior to joing USC for my PhD, I worked as a Software Engineer for 2.5 years at KLA-Tencor’s Wafer Inspection Division on a defect classification software.

I obtained my Master’s degree with specialization in Computer Vision/ Machine Learning from USC. During my study, I had the opportunity to research as part of the Computer Vision Research group at USC Institute for Robotics and Intelligent Systems where I was advised by Dr. Jongmoo Choi under the guidance of Prof. Gerard Medioni. I was also a part time software developer at Laboratory of Neurological Imaging where I worked on project Informatics Visualization in NeuroImaging (INVIZIAN) lead by Prof. John Van Horn.

I completed my Bachelor’s degree in Electronics and Communication from National Institute of Technology, Tiruchrappalli (aka Regional Engineering College, Trichy) where I worked under the advise of Prof. Deivalakshmi and Prof. Palanisamy.