Data Debugging is NP-hard for Classifiers Trained with SGD

2 August 2024

Papers citing "Data Debugging is NP-hard for Classifiers Trained with SGD"

5 / 5 papers shown

Title
If Influence Functions are the Answer, Then What is the Question? Juhan Bae Nathan Ng Alston Lo Marzyeh Ghassemi Roger C. Grosse TDI 95 104 0 12 Sep 2022
Interpretable Data-Based Explanations for Fairness Debugging Romila Pradhan Jiongli Zhu Boris Glavic Babak Salimi 71 57 0 17 Dec 2021
Does the Order of Training Samples Matter? Improving Neural Data-to-Text Generation with Curriculum Learning Ernie Chang Hui-Syuan Yeh Vera Demberg 70 40 0 06 Feb 2021
FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging Han Guo Nazneen Rajani Peter Hase Joey Tianyi Zhou Caiming Xiong TDI 118 116 0 31 Dec 2020
Understanding Black-box Predictions via Influence Functions Pang Wei Koh Percy Liang TDI 219 2,910 0 14 Mar 2017