About me

Hi :) Welcome to my personal webpage which I plan to use for collating my projects list, publications and host my ML/RL technical blogs at one place! Currently I am working at Flipkart as Data Scientist II in Search Ranking Team where I am learning to apply my skills at scale for ranking products for ~100 Million monthly active users at FK app/website. I have done my Masters from Dept. of Computer Science Automation(CSA), Indian Institute of Science, Bangalore. My area of interests interests are Multi-armed Bandits, Explainable ML, Safe Reinforcement Learning, AutoML and Natural Language Processing. In spare time I love to read non-fiction books, watch documentaries and play music. I am also part of a band names Echoes as Rhythm Guitarist, See them here :)

For research collaborations in my areas of interest, feel free to drop mail : ashish “dot” jayant94 “at” gmail “dot” com

Update : My work with Prof. Shalabh Bhatnagar titled “Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm” based on first part of my masters thesis got accepted for publication at NeurIPS 2022 and will be presented at Conference proceedings at New Orleans Convention Center, New Orleans, Lousiana, USA in poster sessions from Nov 29 - Dec 2. See here

Blogs : WIP (Plan : Cross Entropy Optimization in Neural Nets, Conjugate Priors, Beta Distribution, Thompson’s Sampling, Contextual Bandits) Suggest more to ashish “dot” jayant94 “at” gmail “dot” com