Multi-source transfer learning incurs an intrinsic adaptation cost that can exceed one, with phase transitions separating regimes where bias-agnostic estimators match oracle performance from those where they cannot.
hub
Graphical Models for Processing Missing Data
37 Pith papers cite this work, alongside 21 external citations. Polarity classification is still indexing.
37
Pith papers citing it
21
external citations · external index
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Develops stochastic policies and single-basis-function modification for causal inference on functional treatments, proves asymptotic normality and rate double robustness, and applies to NHANES physical activity and mortality data.
A nonparametric sensitivity framework supplies bounds on the controlled direct effect of contagion in fixed-in-time networks by quantifying the latent homophily strength required to explain away observed connected-dyad associations, with a simulation study and application to 2008 U.S. House TARP vot
A Bayesian global Fréchet regression method is introduced via a Fréchet Bayes rule that reduces the problem to scalar tasks, allows prior-data interpolation, and remains valid under moment conditions using weak conditional expectations.
Establishes statistical and computational optimality thresholds for common subspace estimation and inference under varying SNR regimes, including an impossibility result for adaptive confidence intervals below strong inference SNR.
Formulates privacy-constrained advertising measurement as a robust causal decision problem under signal loss and derives a sharp decision frontier separating certifiable from unresolved incrementality claims.
A tuning-parameter-free self-normalized test detects changes in the marginal distribution of object-valued time series under weak dependence, with first nonparametric consistency results for multiple change-point estimation via wild binary segmentation.
Introduces bridge score for covariate balancing in mediator stage and derives sharp pointwise variance bounds on unidentified mediator-outcome confounding with residual budget calibration and Bayesian inference.
Introduces decision-aware proximal bridge learning using a weighted loss and regret bound to enhance optimal treatment selection in settings with hidden confounding.
LGR samples balanced treatment assignments in high-dimensional experiments via continuous relaxation and SGLD, retaining valid inference through randomization tests while being orders of magnitude faster than prior methods.
Derives asymptotic efficiency bounds for a broad class of sequential experimental designs showing no further first-order asymptotic efficiency gains are possible for ATE estimation beyond the Hahn (1998) bound achieved with optimized propensity scores.
Proposes a source-data-free transfer learning framework for sparse single-index models that transfers generalized Stein's lemma summaries and uses a guided MLP for nonlinear adaptation.
WRaPs extends optimally weighted random effect estimators to joint models, providing closed-form solutions for basic cases and MCMC computation for complex ones to predict extreme random effects while accounting for survival data.
Develops TWSF estimator for causal forecasting in panel data by combining synthetic controls with time-series models under low-rank latent factor assumptions, providing finite-sample bounds and asymptotic normality.
A deep learning method amortizes probabilistic XCO2 retrieval from OCO-2 spectra via Laplace approximations and normalizing flows, trained on simulations with model errors to achieve faster inference and better-calibrated uncertainties than operational solvers.
A Bayesian CP tensor factorization model with Poisson rate for occurrence and conditional Gamma for magnitude, with slice-specific dispersion, applied to 60 million international trade flows to recover multiway dependencies.
MTPCA performs sparse PCA on mixed-type data by linking exponential family parameters to shared Gaussian latents and estimating the latent covariance matrix via method of moments.
Proposes and analyzes a homogeneity test using squared L2 distance of empirical EOT maps to uniform-on-ball reference, with FCLT, Gaussian quadratic null limit, consistency, local power, and weighted multiplier bootstrap.
ELCP integrates auxiliary data with a density-ratio-weighted kernel to enhance localized conformal prediction sets, maintaining marginal coverage and improving asymptotic local coverage.
DeSI estimates a single index via deep neural network for conditional Fréchet mean regression in metric spaces, with claimed uniform approximation, convergence rates, and empirical performance on distributions, networks, SPD matrices, and mood data.
Wasserstein least squares extends Euclidean least squares to distribution-valued responses via convex analysis, yielding n^{-1/2} rates under template deformation and faster barycenter rates than prior work.
A recursive Riesz representer-based targeted minimum loss estimation procedure unifies asymptotically efficient estimation of causal estimands such as time-varying treatment effects and mediation effects.
A novel bias-reduced online covariance estimator for SGD achieves convergence rate n to the power (α-1)/2 times square root of log n without second-order derivatives.
Geometric tempering yields exponential convergence bounds for both Wasserstein and Fisher-Rao flows but produces no speedup in the Fisher-Rao metric, with new adaptive schedules derived from the tempered dynamics.
citing papers explorer
-
The Statistical Cost of Adaptation in Multi-Source Transfer Learning
Multi-source transfer learning incurs an intrinsic adaptation cost that can exceed one, with phase transitions separating regimes where bias-agnostic estimators match oracle performance from those where they cannot.
-
Causal Inference for Functional Treatments with Stochastic Policies
Develops stochastic policies and single-basis-function modification for causal inference on functional treatments, proves asymptotic normality and rate double robustness, and applies to NHANES physical activity and mortality data.
-
A Sensitivity Framework for Identifying Contagion under Latent Homophily for Fixed-in-Time Network Analyses, with an Application to U.S. House Congressional Voting
A nonparametric sensitivity framework supplies bounds on the controlled direct effect of contagion in fixed-in-time networks by quantifying the latent homophily strength required to explain away observed connected-dyad associations, with a simulation study and application to 2008 U.S. House TARP vot
-
Bayesian Global Fr\'echet Regression via Weak Conditional Expectations
A Bayesian global Fréchet regression method is introduced via a Fréchet Bayes rule that reduces the problem to scalar tasks, allows prior-data interpolation, and remains valid under moment conditions using weak conditional expectations.
-
Statistically and Computationally Optimal Estimation and Inference of Common Subspaces
Establishes statistical and computational optimality thresholds for common subspace estimation and inference under varying SNR regimes, including an impossibility result for adaptive confidence intervals below strong inference SNR.
-
Privacy-Robust Incrementality Measurement for Advertising Systems under Signal Loss
Formulates privacy-constrained advertising measurement as a robust causal decision problem under signal loss and derives a sharp decision frontier separating certifiable from unresolved incrementality claims.
-
Change-Point Detection for Object-valued Time Series
A tuning-parameter-free self-normalized test detects changes in the marginal distribution of object-valued time series under weak dependence, with first nonparametric consistency results for multiple change-point estimation via wild binary segmentation.
-
Sensitivity analysis for causal mediation: bridge score, sharp sensitivity bounds, and calibration
Introduces bridge score for covariate balancing in mediator stage and derives sharp pointwise variance bounds on unidentified mediator-outcome confounding with residual budget calibration and Bayesian inference.
-
Decision-Aware Proximal Bridge Learning for Optimal Treatment Selection
Introduces decision-aware proximal bridge learning using a weighted loss and regret bound to enhance optimal treatment selection in settings with hidden confounding.
-
Langevin-Gradient Rerandomization
LGR samples balanced treatment assignments in high-dimensional experiments via continuous relaxation and SGLD, retaining valid inference through randomization tests while being orders of magnitude faster than prior methods.
-
Asymptotic Efficiency Bounds for a Class of Experimental Designs
Derives asymptotic efficiency bounds for a broad class of sequential experimental designs showing no further first-order asymptotic efficiency gains are possible for ATE estimation beyond the Hahn (1998) bound achieved with optimized propensity scores.
-
Multi-Source Transfer Learning of Sparse Single-Index Models
Proposes a source-data-free transfer learning framework for sparse single-index models that transfers generalized Stein's lemma summaries and uses a guided MLP for nonlinear adaptation.
-
Improved prediction of extreme random effects in joint models: WRaPs
WRaPs extends optimally weighted random effect estimators to joint models, providing closed-form solutions for basic cases and MCMC computation for complex ones to predict extreme random effects while accounting for survival data.
-
Causal Forecasting in Panel Data: A Two-Way Synthetic Forecasting Approach
Develops TWSF estimator for causal forecasting in panel data by combining synthetic controls with time-series models under low-rank latent factor assumptions, providing finite-sample bounds and asymptotic normality.
-
Amortized Probabilistic Retrieval of Atmospheric CO2 from OCO-2 Spectra Using Deep Learning with Laplace Approximations and Normalizing Flows
A deep learning method amortizes probabilistic XCO2 retrieval from OCO-2 spectra via Laplace approximations and normalizing flows, trained on simulations with model errors to achieve faster inference and better-calibrated uncertainties than operational solvers.
-
Bayesian Poisson-Randomized Gamma Tensor Factorization with Application to International Trade Flows
A Bayesian CP tensor factorization model with Poisson rate for occurrence and conditional Gamma for magnitude, with slice-specific dispersion, applied to 60 million international trade flows to recover multiway dependencies.
-
Model-based sparse mixed-type PCA
MTPCA performs sparse PCA on mixed-type data by linking exponential family parameters to shared Gaussian latents and estimating the latent covariance matrix via method of moments.
-
Two-Sample Homogeneity Test via Entropic Optimal Transport
Proposes and analyzes a homogeneity test using squared L2 distance of empirical EOT maps to uniform-on-ball reference, with FCLT, Gaussian quadratic null limit, consistency, local power, and weighted multiplier bootstrap.
-
Enhanced localized conformal prediction with imperfect auxiliary information
ELCP integrates auxiliary data with a density-ratio-weighted kernel to enhance localized conformal prediction sets, maintaining marginal coverage and improving asymptotic local coverage.
-
Deep Single-Index Fr\'echet Regression
DeSI estimates a single index via deep neural network for conditional Fréchet mean regression in metric spaces, with claimed uniform approximation, convergence rates, and empirical performance on distributions, networks, SPD matrices, and mood data.
-
Wasserstein Least Squares: A Canonical Regression Method for Probability Distributions
Wasserstein least squares extends Euclidean least squares to distribution-valued responses via convex analysis, yielding n^{-1/2} rates under template deformation and faster barycenter rates than prior work.
-
A Riesz Representer Perspective on Targeted Learning
A recursive Riesz representer-based targeted minimum loss estimation procedure unifies asymptotically efficient estimation of causal estimands such as time-varying treatment effects and mediation effects.
-
Refining Covariance Matrix Estimation in Stochastic Gradient Descent Through Bias Reduction
A novel bias-reduced online covariance estimator for SGD achieves convergence rate n to the power (α-1)/2 times square root of log n without second-order derivatives.
-
Properties and limitations of geometric tempering for gradient flow dynamics
Geometric tempering yields exponential convergence bounds for both Wasserstein and Fisher-Rao flows but produces no speedup in the Fisher-Rao metric, with new adaptive schedules derived from the tempered dynamics.
-
Self-separated and self-connected models for mediator and outcome missingness in mediation analysis
Introduces self-separated and self-connected missingness models for mediator and outcome missingness in mediation analysis, enabling identification via conditional independences or shadow variables and extending shadow variable theory.
-
An Instrumental Variable Approach to Account for Informative Treatment Switching in Real-world Evidence
Proposes a doubly robust instrumental variable estimator for treatment effects under informative switching using baseline treatment as instrument and cross-fitting with machine learning.
-
Bayesian Simultaneous Credible Bands for Polynomial Regression
A unified Bayesian framework constructs simultaneous credible bands for univariate polynomial regression that achieve exact posterior coverage and asymptotic frequentist coverage under mild regularity conditions.
-
Adaptive Estimation of Aggregated Values of Conditional Linear Programs
The support function of the identified set for solutions to conditional linear programs is expressed as an average of intersections of regression functions and shown to be a regular parameter admitting standard asymptotic inference.
-
Interaction-Limited Safe Continuous-Time RL for Dynamical Medical Treatment
Introduces Interaction-Limited Safe Continuous-Time RL reformulating medical treatment as an option-based SMDP with trajectory-level safety guarantees and finite-sample learning bounds.
-
Byzantine-Robust Distributed Sparse Learning Revisited
Local L1-regularized robust estimators plus server-side robust aggregation achieve near-optimal rates for high-dimensional sparse learning under Byzantine attacks.
-
A Unified Approach for Computing Wasserstein Barycenters of Discrete and Continuous Measures
A mirror descent algorithm computes exact Wasserstein barycenters for mixed discrete and continuous input measures with convergence guarantees.
-
Feature Screening for High-Dimensional Structural Break Predictive Regression
Develops SICS and RCRS screening methods for consistent selection of sparse active predictors and change points in high-dimensional structural break predictive regressions that may involve stationary or cointegrated series.
-
AI-Assisted Variance Reduction in Randomized Experiments
Including LLM predictions as covariates in standard regression adjustment for randomized experiments reduces variance with a do-no-harm property that reverts to the unadjusted estimator when predictions are uninformative.
-
Reconciling Latent Variables and Networks: Exploring and extending the Psychometric-Toolbox
Network and latent-variable psychometric models are formally related across binary, continuous, and time-series data, and can be productively extended by methods from graph theory, econometrics, and dynamical systems.
-
Active Learning with Bayesian Reasoning: A POGIL-Based Pedagogy in Introductory Statistics
POGIL activity for Bayes' theorem yields similar student outcomes to lectures in quasi-experimental evaluation with Bayesian GLM accounting for demographics.
-
A Guide to Higher-Order Homophily
A survey of existing measures and models for quantifying and generating higher-order homophily and heterophily in hypergraphs.
-
crumble: A comprehensive framework for modern causal mediation analysis with intermediate confounding
The crumble package provides nonparametric tools for estimating natural direct/indirect effects, randomized interventional effects, and recanting-twin effects in mediation analysis, with guidance on identification assumptions and non-binary treatments illustrated via case studies.