Scholar
Harikrishna Narasimhan
Google Scholar ID: 7X_oT4YAAAAJ
Google Research
Citations & Impact
Citations
2,416
H-index
28
i10-index
45
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- 2025: ICLR Outstanding Paper Honorable Mention Award for 'Faster cascades via speculative decoding'.
- 2024: Two journal papers accepted in JMLR and JACM; three papers accepted at ICLR 2024 (including a Spotlight); Senior Area Chair for NeurIPS 2024; granted two US patents (US20240311405A1, US20240135254A1).
- 2023: Area Chair for ICML 2023; invited talk at AAAI Workshop on Deployable AI (DAI) on 'Learning to abstain and beyond'.
- 2022: Granted US patent US20220398506A1; co-organized CVPR 2022 tutorial on 'Deep AUC Maximization'.
- 2021: Area Chair for NeurIPS 2021.
- 2020: Four papers accepted at NeurIPS; top 10% reviewer at NeurIPS, top 33% at ICML; guest lecture at IIT Kharagpur on 'Fairness Goals through Constrained Optimization'; co-authored Google blogpost on TensorFlow Constrained Optimization (TFCO) library.
- 2019: Two oral presentations at NeurIPS (top 0.5%), one oral at ICML (<5%); top 400 reviewer at NeurIPS.
- Selected publications include ICLR 2025 'Faster Cascades via Speculative Decoding', NeurIPS 2020 'Robust Optimization for Fairness with Noisy Protected Groups', and NeurIPS 2019 'On Making Stochastic Classifiers Deterministic' (oral, foundational work for TFCO library).
Co-authors