I am currently a Senior Researcher at Microsoft Research India, where I am part of the ReFoRM team working on Information Retrieval. My current research focuses on the challenges that arise throughout the dual-encoder training pipeline, spanning large-scale training, data quality, negative sampling, and training efficiency.
I completed my Ph.D. in Computer Science at IIT Bombay under the guidance of Prof. Sunita Sarawagi and Prof. Abir De, supported by the Prime Minister’s Research Fellowship (PMRF). My doctoral research was in causal machine learning, with a particular emphasis on Algorithmic Recourse, developing methods that enable human-in-the-loop modifications of input instances to achieve user-specific objectives. My work also explored treatment effect estimation and related problems in causal inference.
More broadly, my research interests span machine learning systems and algorithms, including Federated Learning, representation learning for graph-structured data, and the evaluation of data quality metrics. Before joining IIT Bombay, I spent approximately one and a half years at IBM Research, where I worked on Federated Learning, data quality assessment, and user preference aggregation. I received my Master’s degree from IISc Bangalore, where I worked with Prof. M. Narasimha Murty on learning robust, outlier-aware representations for social networks.
- Machine Learning in general
- Causal Inference
- Algorithmic Recourse
- Federated Learning
-
PhD in CSE, 2021 - 2025
IIT Bombay
-
M.Tech. in Computer Science, 2019
IISc Bangalore
-
B.E. in Computer Science, 2015
CEG, Anna University
Experience
Updates
- 💵 Attended ICML'26 in Seoul, South Korea. Grateful to MSRI for funding the travel.
- 🔊 Delivered a talk on “HOBIT” at IITB and at the Academic Summit held at Microsoft Research India.
- 📃 HOBIT accepted as a spotlight at ICML'26.
- 🔊 Defended my PhD thesis titled “Learning Causal Representations for Robust Algorithmic Recourse” at IIT Bombay.
- 🔊 Presented Root Cause Diagnosis using In-Distribution Interventions (IDI) at RISC 2025.
- 📃 Robust Root Cause Diagnosis using In-Distribution Interventions accepted at ICLR-25.
- 📃 From Search to Sampling: Generative Models for Robust Algorithmic Recourse accepted at ICLR-25.
- 📝 Reviewer for TMLR-25.
- 📝 Reviewer for ICLR-25.
- 📃 Leveraging a Simulator for Learning Causal Representations from Post-Treatment Covariates for CATE accepted at TMLR-25.
- 📃 Tab-Shapley: Identifying Top-k Tabular Data Quality Insights accepted at AAAI-25.
- 💵 Grateful to PMRF for a travel grant to attend NeurIPS-24 in Vienna.
- 📃 Leveraging a Simulator for Learning Causal Representations from Post-Treatment Covariates for CATE accepted at the CRL workshop at NeurIPS-24.
- 📝 Reviewer for NeurIPS-24.
- 💵 Grateful to Microsoft Research India for a travel grant to attend ICML-24 in Vienna.
- 🍁 Started a research internship at Microsoft Research India, working with Amit Sharma on Root Cause Analysis.
- 📃 PairNet: Training with Observed Pairs to Estimate Individual Treatment Effect.
- 💵 Grateful to Microsoft Research India for a travel grant to attend AAAI-24 in Vancouver.
- 📃 Continuous Treatment Effect Estimation Using Gradient Interpolation and Kernel Smoothing accepted at AAAI-24.
- 📃 Gradient Coresets for Federated Learning accepted as a full paper at WACV'24.
- 🔊 Delivered a talk on “Causal Inference” at Amex, Bangalore.
- 🔊 Co-taught a Machine Learning course for Master’s level students in the CSE Department at VJTI Mumbai.
- 🔊 Co-taught a Machine Learning (Theory/Lab) course for UG students in the CSE Department at SSN College of Engineering, Chennai.
- 🔊 Presented a tutorial on Gaussian Processes in CS 337.
- 🔊 Delivered an invited talk on “Learning Recourse in Instance Environments” at Adobe Research.
- 📃 Learning Recourse in Instance Environments to Enhance Prediction Accuracy accepted at NeurIPS'22.
- 🔊 Delivered a talk on Optimal Transport in the CSE Department at IIT Bombay.
- 📝 Reviewer for AAAI 2023 Research Track.
- 📝 Serving on the Program Committee (PC) of AIMLSystems 2022 Research Track.
- 📣 Teaching Linear Algebra for GATE through NPTEL. Videos available here!
- 📃 Federated Learning with Relevant Data accepted at AAAI'22.
- 📝 Delivered a KDD'21 tutorial on data quality.
- 📝 Serving on the PC of CODS-COMAD 2021 Research Track.
- 📝 Serving on the PC of AIMLSystems 2021 Industry Track.
- 🏫 Started a Ph.D. at IIT Bombay.
- 🔊 Delivered a guest lecture on “Data Quality for Machine Learning” at JDBI, Kolkata.
- 🔊 Delivered a guest lecture on “Outsmarting Outliers in Social Networks” at CEG, Chennai.
- 📃 One short paper accepted at ICDE 2021.
- 📃 One research track paper accepted at AAAI 2021.
- 🏫 Graduated with a Master’s from IISc and joined IBM Research.
- 📃 One research track paper accepted at WSDM 2020.
- 📃 One research track paper accepted at AAAI 2019.
Talks
Publications
Patents
Contact
- nlokeshiisc AT gmail.com
- Kanwal Rekhi building, Dept. of CSE, Powai, Mumbai, India 400076