Research highlights

Flexible Data-Adaptive Approaches to Modern Inference: Under this theme, my work focuses on developing new methods for sound statistical inference on data-adaptive targets. These methods draw on ideas from [generative modeling], [privacy and AI]. Common to these techniques is that they bypass the difficult task of deriving typically case-specific analytical descriptions of the selection process.

Key papers:

Sifan Liu, and Snigdha Panigrahi. Flexible Selective Inference with Flow-based Transport Maps . 2025. [arxiv]
Soham Bakshi, and Snigdha Panigrahi. Classification Trees with Valid Inference via the Exponential Mechanism . 2025. [arxiv]

Inference for unsupervised learning algorithms: My more recent efforts focus on developing inferential methodologies for data-adaptive targets arising in various learning settings, including unsupervised learning. This line of work introduces novel inferential techniques for widely used exploratory tools such as [PCA] and [clustering].

Key papers:

Ronan Perry, Snigdha Panigrahi, Jacob Bien, and Daniela Witten. Inference on the proportion of variance explained in principal component analysis. 2025. Journal of the American Statistical Association (Accepted). [link]
Di Wu, Jacob Bien and Snigdha Panigrahi. Hierarchical Clustering with Confidence . 2025. [link]

Antithetic randomization: [Antithetic Gaussian randomization] is proposed as a cross-validation method for reliable assessment of model performance in settings where standard sample splitting is infeasible, such as with non-i.i.d. data. This approach achieves near-zero bias without paying a price in variance, thereby outperforming existing randomization alternatives.

Key papers:

Srijan Chattopadhyay, Sifan Liu, and Snigdha Panigrahi. On the Optimality of Antithetic Randomization for Cross-Validation. 2026 . [link]
Sifan Liu, Snigdha Panigrahi, and Jake A. Soloff. Cross-Validation with Antithetic Gaussian Randomization. 2026. Journal of the Royal Statistical Society Series B (Accepted).[link]

Distribution-free selective inference: This line of research expands the scope of selective inference beyond normal data. My [work] provides a first-of-its-kind theoretical basis for data carving, a new class of inferential methods that, like data splitting, uses a subset of the data for selection but, unlike splitting, utilizes the full dataset for selective (or post-selection) inference.

The proof techniques developed have advanced selective inference in semi- and nonparametric settings where it was previously unavailable, including, for example, [causal effect moderation] and [quantile regression].

Key papers:

Snigdha Panigrahi. Carving model-free inference. 2023. Annals of Statistics. [link]
Soham Bakshi, Walter Dempsey, and Snigdha Panigrahi. Selective Inference for Time-varying Effect Moderation. 2024+. [link]
Yumeng Wang, Snigdha Panigrahi, and Xuming He. Asymptotically-exact selective inference for quantile regression. 2025. Annals of Statistics (Accepted). [link]

Selective inference beyond polyhedral constraints: This line of research develops a simple Gaussian randomization scheme that enables feasible inference for selection events that do not satisfy polyhedral constraints. By contrast, early work in the area, e.g., [Lee et al. (2016)], rely on a polyhedral representation of the selection event.

These randomization techniques make selective inference feasible across a broad range of learning problems, including the selection of [groups of variables] via group lasso–type penalties, models fitted through [multi-task learning], and dependence structure learned through [graph- or network-analysis].

Key papers:

Snigdha Panigrahi, Peter W. Macdonald, and Daniel Kessler. Approximate Post-Selective Inference for Regression with the Group LASSO. 2023. Journal of Machine Learning Research. [link]
Snigdha Panigrahi, Natasha Stewart, Chandra Sripada, and Elizaveta Levina. Selective Inference for Sparse Multitask Regression with Applications in Neuroimaging. 2024. Annals of Applied Statistics. [link]
Yiling Huang, Snigdha Panigrahi, and Walter Dempsey. Selective Inference for Sparse Graphs via Neighborhood Selection. 2025. Electronic Journal of Statistics. [link]
Sofia Guglielmini, Gerda Claeskens, and Snigdha Panigrahi. Selective Inference in Graphical Models via Maximum Likelihood. 2025+. [link]

Tractable and powerful selective inference: My work, under this theme, develops: (i) sampling methods, leveraging the benefits of a full [Bayesian] machinery, (ii) probabilistic [approximation] techniques that rely on convex analysis and large deviation theory, (iii) [exact] methods by identifying an appropriate conditioning set.

These advances have led to a general M-estimation framework for selective inference that accommodates both likelihood-based and more general models, as developed [here].

Key papers:

Snigdha Panigrahi, Jonathan Taylor, and Asaf Weinstein. Integrative methods for post-selection inference under convex constraints. 2021. Annals of Statistics. [link]
Snigdha Panigrahi and Jonathan Taylor. Approximate selective inference via maximum likelihood. 2022. Journal of the American Statistical Association [link]
Snigdha Panigrahi, Kevin Fry, and Jonathan Taylor. Exact Selective Inference with Randomization. 2024. Biometrika. [link]
Yiling Huang, Sarah Pirenne, Snigdha Panigrahi, and Gerda Claeskens. Selective Inference using Randomized Group Lasso Estimators for General Models. 2025. Electronic Journal of Statistics. [link]

Papers and software

New Papers (2026)

Erin Craig, Yiling Huang, and Snigdha Panigrahi. Interpretable AI with Local Distillation. [arxiv]

Srijan Chattopadhyay, Sifan Liu, and Snigdha Panigrahi. On the Optimality of Antithetic Randomization for Cross-Validation. [arxiv]

Soham Bakshi, Lingjun Gao, Zijun Gao, and Snigdha Panigrahi. Flexible Inference for Winners with Conditional Validity. [arxiv]

Ronan Perry, Snigdha Panigrahi, and Daniela Witten. Post-selection inference for penalized M-estimators via score thinning. [arxiv]

Yiling Huang, Snigdha Panigrahi, Guo Yu, and Jacob Bien. Reluctant Interaction Inference after Additive Modeling . Journal of Machine Learning Research (Accepted). 2026. [arxiv]

Sifan Liu, Snigdha Panigrahi, and Jake A. Soloff. Cross-Validation with Antithetic Gaussian Randomization. Journal of the Royal Statistical Society Series B (Accepted). 2026. [arxiv]

Papers (2025)

Di Wu, Jacob Bien and Snigdha Panigrahi. Hierarchical Clustering with Confidence . [arxiv]

Soham Bakshi, and Snigdha Panigrahi. Classification Trees with Valid Inference via the Exponential Mechanism . [arxiv]

Sifan Liu, and Snigdha Panigrahi. Flexible Selective Inference with Flow-based Transport Maps . [arxiv]

Sofia Guglielmini, Gerda Claeskens, and Snigdha Panigrahi. Selective Inference in Graphical Models via Maximum Likelihood [arxiv]

Yiling Huang, Snigdha Panigrahi, and Walter Dempsey. Selective Inference for Sparse Graphs via Neighborhood Selection 2025. Electronic Journal of Statistics. [arxiv][publication]

Ronan Perry, Snigdha Panigrahi, Jacob Bien, and Daniela Witten. Inference on the proportion of variance explained in principal component analysis 2025. Journal of the American Statistical Association. [arxiv] [publication]

Yiling Huang, Sarah Pirenne, Snigdha Panigrahi, and Gerda Claeskens. Selective Inference using Randomized Group Lasso Estimators for General Models 2025. Electronic Journal of Statistics. [arxiv] [publication]

Sifan Liu, and Snigdha Panigrahi. Selective Inference with Distributed Data 2025. Journal of Machine Learning Research. [arxiv] [publication]

Snigdha Panigrahi, Jingshen Wang, and Xuming He. Treatment Effect Estimation via Efficient Data Aggregation 2025. Bernoulli. [arxiv] [publication]

Yumeng Wang, Snigdha Panigrahi, and Xuming He. Asymptotically-exact selective inference for quantile regression 2025. Annals of Statistics. [arxiv][publication]

Papers (2024 and older)

Soham Bakshi, Yiling Huang, Snigdha Panigrahi, and Walter Dempsey. Inference with Randomized Regression Trees 2024. [arxiv]

Soham Bakshi, Walter Dempsey, and Snigdha Panigrahi. Selective Inference for Time-varying Effect Moderation 2024. [arxiv]

Kevin Fry, Snigdha Panigrahi, and Jonathan Taylor. Assumption-Lean Data Fission with Resampled Data (Discussion of Data fission: splitting a single data point) 2024. Journal of the American Statistical Association. [publication]

Snigdha Panigrahi, Kevin Fry, and Jonathan Taylor. Exact Selective Inference with Randomization 2024. Biometrika. [arxiv] [publication]

Snigdha Panigrahi, Natasha Stewart, Chandra Sripada, and Elizaveta Levina. Selective Inference for Sparse Multitask Regression with Applications in Neuroimaging 2024. Annals of Applied Statistics. [arxiv] [publication]

Snigdha Panigrahi. Carving model-free inference 2023. Annals of Statistics. [arxiv] [publication]

Snigdha Panigrahi, Peter W. Macdonald, and Daniel Kessler. Approximate Post-Selective Inference for Regression with the Group LASSO 2023. Journal of Machine Learning Research. [arxiv] [publication]

Snigdha Panigrahi, Shariq Mohammad, Arvind Rao, and Veerabhadran Baladandayuthapani. Integrative Bayesian models using Post-selective Inference: a case study in Radiogenomics 2022. Biometrics. [arxiv] [publication]

Snigdha Panigrahi and Jonathan Taylor. Approximate selective inference via maximum likelihood 2022. Journal of the American Statistical Association [arxiv]; [publication]

Snigdha Panigrahi, Jonathan Taylor, and Asaf Weinstein. Integrative methods for post-selection inference under convex constraints 2021. Annals of Statistics. [arxiv]; [publication]

Snigdha Panigrahi, Parthanil Roy, and Yimin Xiao. Maximal Moments and Uniform Modulus of Continuity for Stable Random Fields 2021. Stochastic processes and their applications. [arxiv]; [publication]

Basil Saeed, Snigdha Panigrahi, and Caroline Uhler. Causal Structure Discovery from Distributions Arising from Mixtures of DAGs 2020. International Conference on Machine Learning. [arxiv]; [publication]

Snigdha Panigrahi, Junjie Zhu, and Chiara Sabatti. Selection-adjusted inference: an application to confidence intervals for cis-eQTL effect sizes 2019. Biostatistics. [arxiv]; [publication]

Qingyuan Zhao and Snigdha Panigrahi. Selective Inference for Effect Modication: An Empirical Investigation 2019. Observational Studies: Special issue devoted to ACIC. [arxiv]; [publication]

Snigdha Panigrahi, Nadia Fawaz, and Ajith Pudhiyaveetil. Temporal Evolution of Behavioral User Personas via Latent Variable Mixture models 2019. IUI Workshops on Exploratory Search and Interactive Data Analytics. [arxiv]; [publication]

Snigdha Panigrahi, Jonathan Taylor, and Sreekar Vadlamani. Kinematic Formula for Heterogeneous Gaussian Related Fields 2018. Stochastic processes and their applications. [arxiv]; [publication]

Snigdha Panigrahi and Jonathan Taylor. Scalable methods for Bayesian selective inference 2018. Electronic Journal of Statistics. [arxiv]; [publication]

Snigdha Panigrahi, Jelena Markovic, and Jonathan Taylor. An MCMC-free approach to post-selective inference 2017. [arxiv]

Xiaoying Tian Harris, Snigdha Panigrahi, Jelena Markovic, Nan Bi, and Jonathan Taylor. Selective sampling after solving a convex problem 2016. [arxiv]

SOFTWARE My contributions to software development in the field of Selective Inference can be tracked here: [Github]

Snigdha Panigrahi

Associate Professor of Statistics

University of Michigan

About me

Research highlights

Papers and software

Teaching

STATS 415 - Data Mining and Machine Learning

Upper-level Undergraduate Course

STATS 600 - Linear Models

Graduate Level Course - Core course on regression for the Statistics Ph.D. program

STATS 605 - Statistical methods for Adaptive Data Analysis

Special Topics Course for PhD students

STATS 280 - Honors Introduction to Statistics & Data Analysis

Lower-level Undergraduate Course for Honors Students

Meet the Team