paper-with-me

Papers

Statistical and Computational Guarantees for Influence Diagnostics

2022-12-08 · Jillian Fisher, Lang Liu, Krishna Pillutla, Yejin Choi, Zaid Harchaoui

Influence diagnostics such as influence functions and approximate maximum influence perturbations are popular in machine learning and in AI domain applications. Influence diagnostics are powerful statistical tools to identify influential datapoints or subsets of datapoints. We establish finite-sample statistical bounds, as well as computational complexity bounds, for influence functions and approximate maximum influence perturbations using efficient inverse-Hessian-vector product implementations. We illustrate our results with generalized linear models and large attention based models on synthetic and real data.

📄 PDF Abstract BibTeX arXiv:2212.04014

Code (1)

jfisher52/influence_theory 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Approximating Full Conformal Prediction at Scale via Influence Functions

2022-02-02 · Javier Abad, Umang Bhatt, Adrian Weller, Giovanni Cherubin

Conformal prediction (CP) is a wrapper around traditional machine learning models, giving coverage guarantees under the sole assumption of exchangeability; in classification problems, for a chosen significance level $\va…

Conformal PredictionPrediction

New $\sqrt{n}$-consistent, numerically stable higher-order influence function estimators

2023-02-16 · Lin Liu, Chang Li

Higher-Order Influence Functions (HOIFs) provide a unified theory for constructing rate-optimal estimators for a large class of low-dimensional (smooth) statistical functionals/parameters (and sometimes even infinite-dim…

Epidemiology

Influence Diagnostics in High-dimensional M-estimation: Precise Asymptotics

2026-07-10 · Hugo Cui arxiv

The impact of a given training point on a statistical model is classically measured through its leave-one-out influence, which quantifies the effect of its removal from the training set on the model accuracy. While the s…

Active Learning

A statistical perspective of sampling scores for linear regression

2015-07-21 · Siheng Chen, Rohan Varma, Aarti Singh, Jelena Kovačević

In this paper, we consider a statistical problem of learning a linear model from noisy samples. Existing work has focused on approximating the least squares solution by using leverage-based scores as an importance sampli…

regression

Noisy but Valid: Robust Statistical Evaluation of LLMs with Imperfect Judges

2026-01-28 · Chen Feng, Minghe Shen, Ananth Balashankar, Carsten Gerner-Beuerle 외 arxiv

Reliable certification of Large Language Models (LLMs)-verifying that failure rates are below a safety threshold-is critical yet challenging. While "LLM-as-a-Judge" offers scalability, judge imperfections, noise, and bia…