Lokesh Nagalapatti
Scholar

Lokesh Nagalapatti

Google Scholar ID: BkkZbo0AAAAJ
Senior Researcher, MSR India
Algorithmic RecourseCausal InferenceInformation Retrieval
Citations & Impact
All-time
Citations
1,070
 
H-index
10
 
i10-index
10
 
Publications
20
 
Co-authors
12
list available
Resume (English only)
Academic Achievements
  • Paper 'Robust Root Cause Diagnosis using In-Distribution Interventions' accepted at ICLR 2025.
  • Paper 'From Search to Sampling: Generative Models for Robust Algorithmic Recourse' accepted at ICLR 2025.
  • Paper 'Leveraging a Simulator for Learning Causal Representations from Post-Treatment Covariates for CATE' accepted at TMLR 2025 and presented at CRL workshop @ NeurIPS 2024.
  • Paper 'Tab-Shapley: Identifying Top-k Tabular Data Quality Insights' accepted at AAAI 2025.
  • Paper 'Continuous Treatment Effect Estimation Using Gradient Interpolation and Kernel Smoothing' accepted at AAAI 2024.
  • Paper 'Gradient Coresets for Federated Learning' accepted as full paper at WACV 2024.
  • Paper 'Learning Recourse in Instance Environments to Enhance Prediction Accuracy' accepted at NeurIPS 2022.
  • Reviewer for TMLR-25, ICLR-25, NeurIPS-24, AAAI 2023.
  • Program Committee member for AIMLSystems 2022 Research Track.
  • Received travel grants from PMRF (for NeurIPS 2024) and Microsoft Research India (for ICML 2024 and AAAI 2024).
  • Presented 'Root Cause Diagnosis using In-Distribution Interventions (IDI)' at RISC 2025.
  • Invited talks on Causal Inference, Optimal Transport, and Algorithmic Recourse at Adobe, Amex, and IIT Bombay.
  • Co-taught Machine Learning courses at VJTI Mumbai and SSN College of Engineering.
Background
  • Currently in the fourth year of PhD at IIT Bombay, India, since 2021.
  • Primary research focuses on Causal Inference and Algorithmic Recourse.
  • Advised by Prof. Sunita Sarawagi and Prof. Abir De.
  • PhD funded by the Prime Minister Research Fellowship (PMRF).
  • Research interests include Machine Learning, Causal Inference, Algorithmic Recourse, and Federated Learning.