publications

You can also view this page organized by publication status or by topic.
Most of my papers are also available on arXiv and Google Scholar.

2024

• Semi-Supervised U-statistics.
  Ilmun Kim, Larry Wasserman, Sivaraman Balakrishnan and Matey Neykov.

• Double Cross-fit Doubly Robust Estimators: Beyond Series Regression.
  Alec McClean, Sivaraman Balakrishnan, Edward Kennedy, Larry Wasserman.

• Causal Inference with High-dimensional Discrete Covariates.
  Zhenghao Zeng, Sivaraman Balakrishnan, Yanjun Han, Edward Kennedy.

• Two-Sample Testing with a Graph-Based Total Variation Integral Probability Metric.
  Alden Green, Sivaraman Balakrishnan and Ryan Tibshirani.

• Stochastic interventions, sensitivity analysis, and optimal transport.
  Alex Levis, Edward Kennedy, Alec McClean, Sivaraman Balakrishnan and Larry Wasserman.

• Central Limit Theorems for Smooth Optimal Transport Maps.
  Tudor Manole, Sivaraman Balakrishnan, Jon Niles-Weed and Larry Wasserman.

• Conservative Inference for Counterfactuals.
  Sivaraman Balakrishnan, Edward Kennedy and Larry Wasserman.

• Causal Effect Estimation after Propensity Score Trimming with Continuous Treatments.
  Zach Branson, Edward Kennedy, Sivaraman Balakrishnan and Larry Wasserman.

• Doubly-robust Inference and Optimality in Structure-Agnostic Models with Smoothness.
  Matteo Bonvini, Edward Kennedy, Oliver Dukes and Sivaraman Balakrishnan.

2023

• Nearly Minimax Optimal Wasserstein Conditional Independence Testing.
  Matey Neykov, Larry Wasserman, Ilmun Kim and Sivaraman Balakrishnan.
  Information and Inference.

• Conditional Independence Testing for Discrete Distributions: Beyond Chi-Squared and G-tests.
  Ilmun Kim, Matey Neykov, Sivaraman Balakrishnan and Larry Wasserman.
  Electronic Journal of Statistics.

• The Fundamental Limits of Structure-Agnostic Functional Estimation.
  Sivaraman Balakrishnan, Ed Kennedy and Larry Wasserman.
  

• Robust Universal Inference.
  Beomjo Park, Sivaraman Balakrishnan and Larry Wasserman.
  

• RLSbench: Domain Adaptation Under Relaxed Label Shift.
  Saurabh Garg, Nick Erickson, James Sharpnack, Alex Smola, Sivaraman Balakrishnan and Zack Lipton.
  International Conference on Machine Learning (ICML) 2023.

• Online Label Shift: Optimal Dynamic Regret meets Practical Algorithms.
  Dheeraj Baby, Saurabh Garg, Tzu-Ching Yen, Sivaraman Balakrishnan, Zachary Chase Lipton, Yu-Xiang Wang.
  Neural Information Processing Systems (NeurIPS) 2023.

• Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shift.
  Saurabh Garg, Amrith Setlur, Virginia Smith, Zack Lipton, Aditi Raghunathan, Sivaraman Balakrishnan.
  Neural Information Processing Systems (NeurIPS) 2023.

• Domain Adaptation under Missingness Shift.
  Helen Zhou, Sivaraman Balakrishnan and Zack Lipton.
  Artificial Intelligence and Statistics (AISTATS) 2023.

2022

• Domain Adaptation under Open Set Label Shift.
  Saurabh Garg, Sivaraman Balakrishnan and Zack Lipton.
  Neural Information Processing Systems (NeurIPS) 2022.

• Median Regularity and Honest Inference.
  Arun Kuchibhotla, Sivaraman Balakrishnan and Larry Wasserman.
  Biometrika, 2023.

• Minimax Rates for Heterogeneous Causal Effect Estimation.
  Ed Kennedy, Sivaraman Balakrishnan and Larry Wasserman.
  Annals of Statistics.

• Leveraging Unlabeled Data to Predict Out-of-Distribution Performance.
  Saurabh Garg, Sivaraman Balakrishnan, Zack Lipton, Behnam Neyshabur and Hanie Sedghi.
  International Conference on Learning Representations (ICLR) 2022.
  This work was also presented at the DistShift workshop at NeurIPS 2021.
  

• No Rose for MLE: Inadmissibility of MLE for Evaluation Aggregation Under Levels of Expertise.
  Charvi Rastogi, Ivan Stelmakh, Nihar Shah and Sivaraman Balakrishnan.
  International Symposium on Information Theory (ISIT), 2022.

• Heavy-tailed Streaming Statistical Estimation.
  Che-Ping Tsai, Adarsh Prasad, Sivaraman Balakrishnan and Pradeep Ravikumar.
  Artificial Intelligence and Statistics (AISTATS) 2022.
  

2021

• Local permutation tests for conditional independence.
  Ilmun Kim, Matey Neykov, Sivaraman Balakrishnan and Larry Wasserman.
  Annals of Statistics, 2022.

• Plugin Estimation of Smooth Optimal Transport Maps.
  Tudor Manole, Sivaraman Balakrishnan, Jonathan Niles-Weed and Larry Wasserman.
  Annals of Statistics.
  Winner of IMS Lawrence D. Brown Student Award.

• The HulC: Confidence Regions from Convex Hulls.
  Arun Kuchibhotla, Sivaraman Balakrishnan and Larry Wasserman.
  Journal of the Royal Statistical Society, Series B.

• Mixture Proportion Estimation and PU Learning: A Modern Approach.
  Saurabh Garg, Yifan Wu, Alex Smola, Sivaraman Balakrishnan and Zack Lipton.
  Neural Information Processing Systems (NeurIPS) 2021.
  

• Minimax Optimal Regression over Sobolev Spaces via Laplacian Eigenmaps on Neighborhood Graphs.
  Alden Green, Sivaraman Balakrishnan and Ryan Tibshirani.
  Information and Inference, 2023.

• RATT: Leveraging Unlabeled Data to Guarantee Generalization.
  Saurabh Garg, Sivaraman Balakrishnan, Zico Kolter and Zack Lipton.
  International Conference on Machine Learning (ICML) 2021.
  This work was also presented at the RobustML workshop at ICLR 2021.
  

• Minimax Optimal Conditional Density Estimation under Total Variation Smoothness.
  Michael Li, Matey Neykov and Sivaraman Balakrishnan.
  To appear in the Electronic Journal of Statistics, 2022.

• Semiparametric Counterfactual Density Estimation.
  Ed Kennedy, Sivaraman Balakrishnan and Larry Wasserman.
  Biometrika, 2023.

• On Proximal Policy Optimization’s Heavy-tailed Gradients.
  Saurabh Garg, Joshua Zhanson, Emilio Parisotto, Adarsh Prasad, Zico Kolter, Sivaraman Balakrishnan, Zack Lipton, Russ Salakhutdinov and Pradeep Ravikumar.
  International Conference on Machine Learning (ICML) 2021.
  This work was also presented at the Science and Engineering of Deep Learning workshop at ICLR 2021.
  

• Gaussian Universal Likelihood Ratio Testing.
  Robin Dunn, Aaditya Ramdas, Sivaraman Balakrishnan and Larry Wasserman.
  To appear in Biometrika.

• Minimax Optimal Conditional Independence Testing.
  Matey Neykov, Sivaraman Balakrishnan and Larry Wasserman.
  Annals of Statistics. Vol. 49, No. 4 (2021), 2151 - 2177.

• Minimax Optimal Regression over Sobolev Spaces via Laplacian Regularization on Neighborhood Graphs.
  Alden Green, Sivaraman Balakrishnan and Ryan Tibshirani.
  Artificial Intelligence and Statistics (AISTATS) 2021.
  

2020

• Regression with Comparisons: Escaping the Curse of Dimensionality with Ordinal Information.
  Yichong Xu, Sivaraman Balakrishnan, Artur Dubrawski and Aarti Singh.
  To appear in the Journal of Machine Learning Research, 2020.
  A short version of this paper appeared in ICML 2018 and was presented at Asilomar 2018.

• Universal Inference.
  Larry Wasserman, Aaditya Ramdas and Sivaraman Balakrishnan.
  Proceedings of the National Academy of Sciences, Vol. 117, No. 29, 2020.

• Robust Estimation via Robust Gradient Estimation.
  Adarsh Prasad, Arun Sai Suggala, Sivaraman Balakrishnan and Pradeep Ravikumar.
  Journal of the Royal Statistical Society, Series B, Vol. 83, Issue 3, 2020.

• Sharp instruments for classifying compliers and generalizing causal effects.
  Ed Kennedy, Sivaraman Balakrishnan and Max G’Sell.
  Annals of Statistics, Vol. 48, No. 4, 2020.

• Robust Multivariate Nonparametric Tests via Projection-Averaging.
  Ilmun Kim, Sivaraman Balakrishnan and Larry Wasserman.
  To appear in the Annals of Statistics, 2020.

• Discussion of ‘‘On nearly assumption-free tests of nominal confidence interval coverage for causal parameters estimated by machine learning’’.
  Ed Kennedy, Sivaraman Balakrishnan and Larry Wasserman.
  To appear in Statistical Science.

• Two-sample testing on ranked preference data and the role of modeling assumptions.
  Charvi Rastogi, Sivaraman Balakrishnan, Nihar Shah and Aarti Singh.
  International Symposium on Information Theory (ISIT), 2020.

• On Learning Ising Models under Huber’s Contamination Model.
  Adarsh Prasad, Vishwak Srinivasan, Sivaraman Balakrishnan and Pradeep Ravikumar.
  Neural Information Processing Systems (NeurIPS) 2020.
  

• Minimax optimality of permutation tests.
  Ilmun Kim, Sivaraman Balakrishnan and Larry Wasserman.
  To appear in the Annals of Statistics.
  Winner of IMS Lawrence D. Brown Student Award.

• A unified view of label shift estimation.
  Saurabh Garg, Yifan Wu, Sivaraman Balakrishnan and Zack Lipton.
  Neural Information Processing Systems (NeurIPS) 2020.
  This work was also presented at the Uncertainty and Robustness in Deep Learning workshop at ICML 2020.
  

• A Robust Univariate Mean Estimator is All You Need.
  Adarsh Prasad, Sivaraman Balakrishnan and Pradeep Ravikumar.
  Artificial Intelligence and Statistics (AISTATS) 2021.
  

2019

• Low Permutation-rank Matrices: Structural Properties and Noisy Completion.
  Nihar Shah, Sivaraman Balakrishnan and Martin J. Wainwright.
  Journal of Machine Learning Research, Vol. 20, No. 101, 2019.
  A short version appear at the International Symposium on Information Theory (ISIT) 2018.

• Local Spectral Clustering of Density Upper Level Sets.
  Alden Green, Sivaraman Balakrishnan and Ryan Tibshirani.
  To appear in the Journal of Machine Learning Research, 2021.
  

• Gaussian Mixture Clustering Using Relative Tests of Fit.
  Purvasha Chakravarti, Sivaraman Balakrishnan and Larry Wasserman.

• Minimax Confidence Intervals for the Sliced Wasserstein Distance.
  Tudor Manole, Sivaraman Balakrishnan and Larry Wasserman.

• Interactive Martingale Tests for the Global Null.
  Boyan Duan, Aaditya Ramdas, Sivaraman Balakrishnan and Larry Wasserman.
  Electronic Journal of Statistics, Vol. 14, 2020.
  

• Path Length Bounds for Gradient Descent and Flow.
  Chirag Gupta, Sivaraman Balakrishnan and Aaditya Ramdas.
  Journal of Machine Learning Research, Vol. 22, No. 68, 2021.
  

• A Unified Approach to Robust Mean Estimation.
  Adarsh Prasad, Sivaraman Balakrishnan and Pradeep Ravikumar.

• Robust Nonparametric Regression under Huber’s Contamination Model.
  Simon S. Du, Yining Wang, Sivaraman Balakrishnan, Pradeep Ravikumar and Aarti Singh.

• A Permutation-based Model for Crowd Labeling: Optimal Estimation and Robustness.
  Nihar Shah, Sivaraman Balakrishnan, Martin J. Wainwright.
  IEEE Transactions on Information Theory, Vol. 67, Issue 6, 2021.
  

• Optimization of Smooth Functions with Noisy Observations: Local Minimax Rates.
  Yining Wang, Sivaraman Balakrishnan, Aarti Singh.
  IEEE Transactions on Information Theory, Vol. 65, Issue 11, 2019.
  A short version of this paper appeared in NeurIPS 2018.

• Rate Optimal Estimation and Confidence Intervals for High-dimensional Regression with Missing Covariates.
  Yining Wang, Jialei Wang, Sivaraman Balakrishnan and Aarti Singh.
  Journal of Multivariate Analysis, Vol. 174, 2019.

• Feeling the Bern: Adaptive Estimators for Bernoulli Probabilities of Pairwise Comparisons.
  Nihar Shah, Sivaraman Balakrishnan, Martin J. Wainwright.
  IEEE Transactions on Information Theory, Vol. 65, Issue 8, 2019.
  A short version of this paper appeared in the International Symposium on Information Theory (ISIT) 2016.

• Goodness-of-fit Testing for Densities and High-dimensional Multinomials: Sharp Local Minimax Rates.
  Sivaraman Balakrishnan and Larry Wasserman.
  Annals of Statistics, Vol. 47, No. 4 (2019), 1893-1927.

• Hypothesis Testing for High-Dimensional Multinomials: A Selective Review.
  Sivaraman Balakrishnan and Larry Wasserman.
  Annals of Applied Statistics, Vol. 12, No. 2 (2018), pp. 727-749.
  In a special section in memory of Steve Fienberg.

2018

• How Many Samples are Needed to Estimate a Convolutional Neural Network?
  Simon Du, Yining Wang, Xiyu Zhai, Sivaraman Balakrishnan, Ruslan Salakhutdinov and Aarti Singh.
  Neural Information Processing Systems (NeurIPS) 2018.
  Winner of an NVIDIA Pioneer Award. Forbes article.

• Local White Matter Architecture Defines Functional Brain Dynamics.
  Yo Joong Choe, Sivaraman Balakrishnan, Aarti Singh, Jean M. Vettel and Tim Verstynen.
  IEEE International Conference on Systems, Man, and Cybernetics (SMC) 2018.
  Winner of the Franklin V. Taylor Memorial Best Paper Award. Description.

• Stochastic Zeroth-order Optimization in High Dimensions.
  Yining Wang, Simon Du, Sivaraman Balakrishnan and Aarti Singh.
  Artificial Intelligence and Statistics (AISTATS) 2018.

2017

• Statistical Guarantees for the EM Algorithm: From Population to Sample-based Analysis.
  Sivaraman Balakrishnan, Martin J. Wainwright and Bin Yu.
  Annals of Statistics, Vol. 45, Number 1 (2017), 77-120.
  Winner of an International Consortium of Chinese Mathematicians Distinguished Paper Award.

• Computationally Efficient Robust Estimation of Sparse Functionals.
  Simon Du, Sivaraman Balakrishnan and Aarti Singh.
  Conference on Learning Theory (COLT) 2017. Appeared merged with this paper.

• Recovering Block-Structured Activations using Compressive Measurements.
  Sivaraman Balakrishnan, Mladen Kolar, Alessandro Rinaldo and Aarti Singh.
  Electronic Journal of Statistics, Vol. 11, No. 1 (2017), pp. 2647-2678.

• Statistical and Computational Guarantees for the Baum-Welch Algorithm.
  Fanny Yang, Sivaraman Balakrishnan and Martin J. Wainwright.
  Journal of Machine Learning Research, Vol. 18 (2017) pp. 1-53. A short version of this paper appeared at Allerton, 2015, and was presented at the Workshop on Non-convex Optimization for Machine Learning: Theory and Practice in Neural Information Processing Systems (NIPS) 2015.

• Biases in Data-Driven Networking, and What to Do About Them.
  Mihovil Bartulovic, Junchen Jiang, Sivaraman Balakrishnan, Vyas Sekar and Bruno Sinopoli.
  HotNets 2017.

• Discussion of “Data-driven confounder selection via Markov and Bayesian networks” by Jenny Haggstrom.
  Ed Kennedy and Sivaraman Balakrishnan.
  Biometrics, 2017.

2016

• Stochastically Transitive Models for Pairwise Comparisons: Statistical and Computational Issues.
  Nihar Shah, Sivaraman Balakrishnan, Adityanand Guntuboyina, Martin J. Wainwright.
  IEEE Transactions on Information Theory, Vol. 32, Issue 2 (2016) pp. 934-959.
  A short version of this paper appeared at International Conference on Machine Learning (ICML), 2016.

• Estimation from Pairwise Comparisons: Sharp Minimax Bounds with Topology Dependence.
  Nihar Shah, Sivaraman Balakrishnan, Joseph Bradley, Abhay Parekh, Kannan Ramchandran and Martin J. Wainwright.
  Journal of Machine Learning Research, Vol. 17, Number 58 (2016) pp. 1-47.
  A short version of this paper appeared at Artificial Intelligence and Statistics (AISTATS), 2015. This paper was also presented at the Workshop on Non-convex Optimization for Machine Learning: Theory and Practice and at the Workshop on Machine Learning for eCommerce in Neural Information Processing Systems (NIPS) 2015.

• Local Maxima in the Likelihood of Gaussian Mixture Models: Structural Results and Algorithmic Consequences.
  Chi Jin, Yuchen Zhang, Sivaraman Balakrishnan, Martin J. Wainwright and Michael Jordan.
  Neural Information Processing Systems (NIPS) 2016.

• Statistical Inference for Cluster Trees.
  Jisu Kim, Yen-Chi Chen, Sivaraman Balakrishnan, Alessandro Rinaldo, Larry Wasserman.
  Neural Information Processing Systems (NIPS) 2016.

• Arbitrage-Free Combinatorial Market Making via Integer Programming.
  Christian Kroer, Miroslav Dudik, Sebastien Lahaie, Sivaraman Balakrishnan.
  Conference on Economics and Computation (EC) 2016.

2014

• Statistical Inference For Persistent Homology: Confidence Sets For Persistence Diagrams.
  Brittany Fasy, Fabrizio Lecci, Alessandro Rinaldo, Larry Wasserman, Sivaraman Balakrishnan and Aarti Singh.
  Annals of Statistics, Vol. 42, Number 6 (2014), 2301-2339.

• Some Scaling Laws for MOOC Assessments.
  Nihar Shah, Joseph Bradley, Sivaraman Balakrishnan, Abhay Parekh, Kannan Ramchandran and Martin J. Wainwright.
  Knowledge Discovery and Data Mining (KDD) 2014. Workshop on Data Mining for Educational Assessment and Feedback.

• Tight Lower Bounds for Homology Inference.
  Sivaraman Balakrishnan, Alessandro Rinaldo, Aarti Singh and Larry Wasserman.
  This short note, not intended for publication, improves the lower bounds in our earlier paper.

2013

• PhD Thesis. Finding and Leveraging Structure in Learning Problems.
  Thesis committee: Jaime G. Carbonell, John Lafferty, Aarti Singh, Martin J. Wainwright and Larry Wasserman.
  

• Cluster trees on manifolds.
  Sivaraman Balakrishnan, Srivatsan Narayanan, Alessandro Rinaldo, Aarti Singh and Larry Wasserman.
  Neural Information Processing Systems (NIPS) 2013.

2012

• Minimax rates for homology inference.
  Sivaraman Balakrishnan, Alessandro Rinaldo, Don Sheehy, Aarti Singh and Larry Wasserman.
  Artifical Intelligence and Statistics (AISTATS) 2012.

• Sparse additive functional and kernel CCA.
  Sivaraman Balakrishnan, Kriti Puniyani and John Lafferty.
  International Conference on Machine Learning (ICML) 2012.

• Efficient Active Algorithms for Hierarchical Clustering.
  Akshay Krishnamurthy, Sivaraman Balakrishnan, Min Xu and Aarti Singh.
  International Conference on Machine Learning (ICML) 2012.

• Optimal kernel choice for large-scale two-sample tests.
  Arthur Gretton, Bharath Sriperumbudur, Dino Sejdinovic, Heiko Strathmann, Sivaraman Balakrishnan and Kenji Fukumizu.
  Neural Information Processing Systems (NIPS) 2012.

• Completion of high-rank ultrametric matrices using selective entries.
  Aarti Singh, Akshay Krishnamurthy, Sivaraman Balakrishnan and Min Xu.
  IEEE International conference on Speech and Communications (SPCOM) 2012.

2011

• Learning Generative Models for Protein Fold Families.
  Sivaraman Balakrishnan, Hetu Kamisetty, Jaime G. Carbonell, S.I. Lee and Chris Langmead.
  Proteins, Vol 79, Issue 4 (2011), pp 1061-1078. A short version of this paper appeared in 3D Structural Bioinformatics and Computational Biophysics (3DSIG), 2010.

• Noise Thresholds for Spectral Clustering.
  Sivaraman Balakrishnan, Min Xu, Akshay Krishnamurthy and Aarti Singh.
  Neural Information Processing Systems (NIPS) 2011.

• Minimax Localization of Structural Information in Large Noisy Matrices.
  Sivaraman Balakrishnan, Mladen Kolar, Alessandro Rinaldo and Aarti Singh.
  Neural Information Processing Systems (NIPS) 2011.

• Statistical and computational tradeoffs in bi-clustering.
  Sivaraman Balakrishnan, Mladen Kolar, Alessandro Rinaldo, Aarti Singh and Larry Wasserman.
  Workshop on Computational Trade-offs in Statistical Learning, Neural Information Processing Systems (NIPS) 2011.

2009

• Alternative Paths in HIV-1 Targeted Human Signal Transduction Pathways.
  Sivaraman Balakrishnan, Oznur Tastan, Jaime G. Carbonell and Judith Klein-Seetharaman.
  BMC Genomics. Vol. 10 (2009), Supplement 3. A short version of this paper appeared in the International Conference on Bioinformatics (InCoB) 2009.