Develops single-world marginal separable effects as full-population causal estimands for outcomes truncated by death, provides identification and estimation results, and demonstrates them via reanalysis of a prostate cancer trial.
Title resolution pending
18 Pith papers cite this work. Polarity classification is still indexing.
18
Pith papers citing it
years
2026 18representative citing papers
Panel Flow Matching is a generative method to estimate panel densities from longitudinal data with statistical guarantees under irregular sampling, supporting completion, synthetic data, and classification.
ABGD parametrizes piecewise linear functions as difference of max-affine functions and converges linearly to an epsilon-accurate solution with O(d max(sigma/epsilon,1)^2) samples under sub-Gaussian noise, which is minimax optimal up to logs.
CorrDP relaxes standard differential privacy by incorporating feature correlations, enabling distance-dependent noise in DP-ERM for better privacy-utility tradeoffs.
An efficient algorithm recovers phylogenetic trees from Θ(n) noisy quartets under random classification noise, matching the information-theoretic lower bound and achieving near-optimal quartet distance.
A doubly cross-fit DR sieve learner identifies and estimates within-stratum heterogeneous treatment effects under principal ignorability and odds-ratio sensitivity, with oracle rates and uniform bands.
MAPLE estimates conditional class probabilities by local averaging over Mapper-graph neighborhoods with data-driven cover selection and proves consistency under regularity conditions.
Exchangeable bootstrap combined with box calibration produces simultaneous confidence bands for the cumulative hazard that attain nominal asymptotic coverage and closer-to-nominal performance in simulations than prior methods.
DECO is a sparse MoE architecture with ReLU-based routing, learnable expert scaling, and NormSiLU activation that matches dense Transformer performance at 20% expert activation and delivers 2.93x speedup on Jetson AGX Orin.
DKPS-based methods predict new model benchmark scores using cached responses, matching baseline mean absolute error with substantially fewer queries and an offline query selection approach.
Triplet constraints realizable in D-dimensional Euclidean space cannot be preserved above 50% accuracy by any embedding of dimension at most cD for constant c<1, with UGC-hardness preventing better polynomial-time solutions in any dimension.
A new adaptive variance estimator for relative sparsity coefficients is introduced that fully utilizes the prior asymptotic normality theorem and incorporates variable selection effects.
A semi-supervised kernel two-sample test integrates unlabeled covariate data to achieve asymptotic normality under the null, higher power than standard kernel tests, and consistency against fixed and local alternatives.
ParamBoost improves GAMs by fitting piecewise cubic polynomials via gradient boosting and supports constraints for continuity, monotonicity, convexity, and feature interactions.
Media sentiment indicators from Canadian news, when added to a New Keynesian model with endogenous central-bank response, improve out-of-sample forecasts and account for part of monetary-policy propagation to output and prices.
Provides necessary and sufficient conditions for ATE identifiability under selection bias by characterizing propensity and selection probabilities via weak assumptions on probability classes.
Aliphatic side chains on PAHs shift certain infrared band intensity ratios, especially in small molecules, which can mislead ionization-state estimates, though the main diagnostic grid still applies with possible calibration.
On five tabular security datasets at 10% labels, tuning only the classifier with Bayesian optimization recovers a median 86% of the gains from full joint SSL-classifier optimization.
citing papers explorer
-
Causal Inference for All: Marginal Estimands for Outcomes Truncated by Death
Develops single-world marginal separable effects as full-population causal estimands for outcomes truncated by death, provides identification and estimation results, and demonstrates them via reanalysis of a prostate cancer trial.
-
Panel Flow Matching: A Generative Approach to Learning Distributions of Longitudinal Data
Panel Flow Matching is a generative method to estimate panel densities from longitudinal data with statistical guarantees under irregular sampling, supporting completion, synthetic data, and classification.
-
Locally Near Optimal Piecewise Linear Regression in High Dimensions via Difference of Max-Affine Functions
ABGD parametrizes piecewise linear functions as difference of max-affine functions and converges linearly to an epsilon-accurate solution with O(d max(sigma/epsilon,1)^2) samples under sub-Gaussian noise, which is minimax optimal up to logs.
-
Integrating Feature Correlation in Differential Privacy with Applications in DP-ERM
CorrDP relaxes standard differential privacy by incorporating feature correlations, enabling distance-dependent noise in DP-ERM for better privacy-utility tradeoffs.
-
Optimal Phylogenetic Reconstruction from Sampled Quartets
An efficient algorithm recovers phylogenetic trees from Θ(n) noisy quartets under random classification noise, matching the information-theoretic lower bound and achieving near-optimal quartet distance.
-
Doubly cross-fit debiased machine learning of heterogeneous treatment effects under principal stratification
A doubly cross-fit DR sieve learner identifies and estimates within-stratum heterogeneous treatment effects under principal ignorability and odds-ratio sensitivity, with oracle rates and uniform bands.
-
MAPLE: Mapper Based Localized Prediction with Data Driven Cover Selection for High dimensional Data
MAPLE estimates conditional class probabilities by local averaging over Mapper-graph neighborhoods with data-driven cover selection and proves consistency under regularity conditions.
-
Simultaneous confidence bands for cumulative hazard via exchangeable bootstrap and box calibration
Exchangeable bootstrap combined with box calibration produces simultaneous confidence bands for the cumulative hazard that attain nominal asymptotic coverage and closer-to-nominal performance in simulations than prior methods.
-
DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices
DECO is a sparse MoE architecture with ReLU-based routing, learnable expert scaling, and NormSiLU activation that matches dense Transformer performance at 20% expert activation and delivers 2.93x speedup on Jetson AGX Orin.
-
Query-efficient model evaluation using cached responses
DKPS-based methods predict new model benchmark scores using cached responses, matching baseline mean absolute error with substantially fewer queries and an offline query selection approach.
-
Provable Accuracy Collapse in Embedding-Based Representations under Dimensionality Mismatch
Triplet constraints realizable in D-dimensional Euclidean space cannot be preserved above 50% accuracy by any embedding of dimension at most cD for constant c<1, with UGC-hardness preventing better polynomial-time solutions in any dimension.
-
An adaptive variance estimator for relative sparsity
A new adaptive variance estimator for relative sparsity coefficients is introduced that fully utilizes the prior asymptotic normality theorem and incorporates variable selection effects.
-
A Semi-Supervised Kernel Two-Sample Test
A semi-supervised kernel two-sample test integrates unlabeled covariate data to achieve asymptotic normality under the null, higher power than standard kernel tests, and consistency against fixed and local alternatives.
-
ParamBoost: Gradient Boosted Piecewise Cubic Polynomials
ParamBoost improves GAMs by fitting piecewise cubic polynomials via gradient boosting and supports constraints for continuity, monotonicity, convexity, and feature interactions.
-
Monetary Policy in the Media Spotlight: Sentiments, Signals, and Economic Impact
Media sentiment indicators from Canadian news, when added to a New Keynesian model with endogenous central-bank response, improve out-of-sample forecasts and account for part of monetary-policy propagation to output and prices.
-
Towards a holistic understanding of Selection Bias for Causal Effect Identification
Provides necessary and sufficient conditions for ATE identifiability under selection bias by characterizing propensity and selection probabilities via weak assumptions on probability classes.
-
The Influence of Aliphatic Components on the Aromatic Emission Characteristics of Polycyclic Aromatic Hydrocarbons
Aliphatic side chains on PAHs shift certain infrared band intensity ratios, especially in small molecules, which can mislead ionization-state estimates, though the main diagnostic grid still applies with possible calibration.
-
SemiScope: Disentangling Classifier Tuning and Joint Optimization in Semi-Supervised Security Classification
On five tabular security datasets at 10% labels, tuning only the classifier with Bayesian optimization recovers a median 86% of the gains from full joint SSL-classifier optimization.