Statistical Inference for Image Classification, Language Reasoning, and Counterfactual Estimation

Loading...
Thumbnail Image

Files

TR Number

Date

2026-06-15

Journal Title

Journal ISSN

Volume Title

Publisher

Virginia Tech

Abstract

This dissertation addresses three interconnected challenges in statistical inference and machine learning: uncertainty quantification under distribution shift, robust causal estimation in panel data, and reliable confidence estimation for large language models. The first contribution introduces DPI-RG, a distribution-free framework for constructing predictive sets for high-dimensional data under distribution shifts. Using a conditional Wasserstein round-trip generative model, DPI-RG maps data to a lower-dimensional latent space where test statistics asymptotically follow a Chi-square distribution, yielding theoretically guaranteed p-values. The framework exhibits strong robustness to outliers and target shifts without requiring outlier labels during training. The second contribution presents CONCORD, a confidence estimation framework for large language models that represents responses as semantic distributions over constituent clauses rather than single embedding vectors. By combining Sentence Mover's Distance with Symbolic Answer Match, CONCORD captures both structural divergence and discrete answer agreement, producing calibrated confidence scores that substantially outperform logit-based and embedding-based baselines on mathematical reasoning benchmarks. The third contribution proposes an Linfty-regularized Synthetic Control method that bridges the sparse weighting of traditional synthetic control and the denser, more robust weighting of Difference-in-Differences. By distributing weights more evenly across control units while remaining data-driven, the method improves robustness and interpretability while increasing the likelihood of satisfying the parallel trends assumption.

Description

Keywords

Statistical Inference for Image Classification, Language Reasoning, and Counterfactual Estimation

Citation