paper-with-me

홈 › Papers

Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments

2022-06-20 · JinKun Lin, Anqi Zhang, Mathias Lecuyer, Jinyang Li, Aurojit Panda, Siddhartha Sen

We develop a new, principled algorithm for estimating the contribution of training data points to the behavior of a deep learning model, such as a specific prediction it makes. Our algorithm estimates the AME, a quantity that measures the expected (average) marginal effect of adding a data point to a subset of the training data, sampled from a given distribution. When subsets are sampled from the uniform distribution, the AME reduces to the well-known Shapley value. Our approach is inspired by causal inference and randomized experiments: we sample different subsets of the training data to train multiple submodels, and evaluate each submodel's behavior. We then use a LASSO regression to jointly estimate the AME of each data point, based on the subset compositions. Under sparsity assumptions ($k \ll N$ datapoints have large AME), our estimator requires only $O(k\log N)$ randomized submodel trainings, improving upon the best prior Shapley value estimators.

📄 PDF Abstract BibTeX arXiv:2206.10013

Code (1)

lazycal/ame 공식 구현 pytorch

Tasks

Causal Inference

Similar Papers 제목 키워드 기반

Individual Calibration with Randomized Forecasting

2020-06-18 · ICML 2020 1 · Shengjia Zhao, Tengyu Ma, Stefano Ermon

Machine learning applications often require calibrated predictions, e.g. a 90\% credible interval should contain the true outcome 90\% of the times. However, typical definitions of calibration only require this to hold o…

Decision MakingFairnessregression

Measuring Equality in Machine Learning Security Defenses: A Case Study in Speech Recognition

2023-02-17 · Luke E. Richards, Edward Raff, Cynthia Matuszek

Over the past decade, the machine learning security community has developed a myriad of defenses for evasion attacks. An understudied question in that community is: for whom do these defenses defend? This work considers …

Adversarial RobustnessFairnessspeech-recognitionSpeech Recognition

Why do Random Forests Work? Understanding Tree Ensembles as Self-Regularizing Adaptive Smoothers

2024-02-02 · Alicia Curth, Alan Jeffares, Mihaela van der Schaar

Despite their remarkable effectiveness and broad application, the drivers of success underlying ensembles of trees are still not fully understood. In this paper, we highlight how interpreting tree ensembles as adaptive a…

Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothing

2019-12-20 · ICLR 2020 1 · Jinyuan Jia, Xiaoyu Cao, Binghui Wang, Neil Zhenqiang Gong

It is well-known that classifiers are vulnerable to adversarial perturbations. To defend against adversarial perturbations, various certified robustness results have been derived. However, existing certified robustnesses…

The Framework That Survives Bad Models: Human-AI Collaboration For Clinical Trials

2025-10-08 · Yao Chen, David Ohlssen, Aimee Readie, Gregory Ligozio 외 arxiv

Artificial intelligence (AI) holds great promise for supporting clinical trials, from patient recruitment and endpoint assessment to treatment response prediction. However, deploying AI without safeguards poses significa…