Harikrishna Narasimhan

Better autoregressive regression with LLMs via regression-aware fine-tuning ICLR 2025 Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation ICML 2025 Faster Cascades via Speculative Decoding ICLR 2025 Consistent Multiclass Algorithms for Complex Metrics and Constraints JMLR 2024 Language Model Cascades: Token-Level Uncertainty And Beyond ICLR 2024 Learning to Reject Meets Long-tail Learning ICLR 2024 Plugin estimators for selective classification with out-of-distribution detection ICLR 2024 Regression Aware Inference with LLMs EMNLP 2024 Distributionally Robust Post-hoc Classifiers under Prior Shifts ICLR 2023 Robust distillation for worst-class performance: on the interplay between teacher and student objectives UAI 2023 When Does Confidence-Based Cascade Deferral Suffice? NeurIPS 2023 Churn Reduction via Distillation ICLR 2022 Post-hoc estimators for learning to defer to an expert NeurIPS 2022 Quadratic metric elicitation for fairness and beyond UAI 2022 Implicit rate-constrained optimization of non-decomposable objectives ICML 2021 Optimizing Black-box Metrics with Iterative Example Weighting ICML 2021 Training Over-parameterized Models with Non-decomposable Objectives NeurIPS 2021 Approximate Heavily-Constrained Learning with Lagrange Multiplier Models NeurIPS 2020 Consistent Plug-in Classifiers for Complex Objectives and Constraints NeurIPS 2020 Fair Performance Metric Elicitation NeurIPS 2020 Optimizing Black-box Metrics with Adaptive Surrogates ICML 2020 Pairwise Fairness for Ranking and Regression AAAI 2020 Robust Optimization for Fairness with Noisy Protected Groups NeurIPS 2020 Metric-Optimized Example Weights ICML 2019 On Making Stochastic Classifiers Deterministic NeurIPS 2019 Optimal Auctions through Deep Learning ICML 2019 Optimizing Generalized Rate Metrics with Three Players NeurIPS 2019 Deep Learning for Multi-Facility Location Mechanism Design IJCAI 2018 Learning with Complex Loss Functions and Constraints AISTATS 2018 Automated Mechanism Design without Money via Machine Learning IJCAI 2016 Consistent Multiclass Algorithms for Complex Performance Measures ICML 2015 Learnability of Influence in Networks NeurIPS 2015 Optimizing Non-decomposable Performance Measures: A Tale of Two Classes ICML 2015 Surrogate Functions for Maximizing Precision at the Top ICML 2015 GEV-Canonical Regression for Accurate Binary Class Probability Estimation when One Class is Rare ICML 2014 Online and Stochastic Gradient Methods for Non-decomposable Loss Functions NeurIPS 2014 On the Statistical Consistency of Plug-in Classifiers for Non-decomposable Performance Measures NeurIPS 2014 A Structural SVM Based Approach for Optimizing Partial AUC ICML 2013 On the Relationship Between Binary Classification, Bipartite Ranking, and Binary Class Probability Estimation NeurIPS 2013 On the Statistical Consistency of Algorithms for Binary Classification under Class Imbalance ICML 2013