paper-with-me

홈 › Papers

Attesting Distributional Properties of Training Data for Machine Learning

2023-08-18 · Vasisht Duddu, Anudeep Das, Nora Khayata, Hossein Yalame, Thomas Schneider, N. Asokan

The success of machine learning (ML) has been accompanied by increased concerns about its trustworthiness. Several jurisdictions are preparing ML regulatory frameworks. One such concern is ensuring that model training data has desirable distributional properties for certain sensitive attributes. For example, draft regulations indicate that model trainers are required to show that training datasets have specific distributional properties, such as reflecting diversity of the population. We propose the notion of property attestation allowing a prover (e.g., model trainer) to demonstrate relevant distributional properties of training data to a verifier (e.g., a customer) without revealing the data. We present an effective hybrid property attestation combining property inference with cryptographic mechanisms.

📄 PDF Abstract BibTeX arXiv:2308.09552

Code (1)

ssg-research/distribution-attestation 공식 구현 pytorch

Tasks

Diversity

Similar Papers 제목 키워드 기반

Distributionally Robust Bayesian Optimization with $\varphi$-divergences

2022-03-04 · NeurIPS 2023 11

The study of robustness has received much attention due to its inevitability in data-driven settings where many systems face uncertainty. One such example of concern is Bayesian Optimization (BO), where uncertainty is mu…

Bayesian Optimization

A Distributional Framework for Data Valuation

2020-02-27 · ICML 2020 1 · Amirata Ghorbani, Michael P. Kim, James Zou

Shapley value is a classic notion from game theory, historically used to quantify the contributions of individuals within groups, and more recently applied to assign values to data points when training machine learning m…

Data Valuation

Learning Against Distributional Uncertainty: On the Trade-off Between Robustness and Specificity

2023-01-31 · Shixiong Wang, Haowei Wang, Xinke Li, Jean Honorio

Trustworthy machine learning aims at combating distributional uncertainties in training data distributions compared to population distributions. Typical treatment frameworks include the Bayesian approach, (min-max) distr…

Generalization BoundsSpecificity

Estimating Distributional Treatment Effects in Randomized Experiments: Machine Learning for Variance Reduction

2024-07-22 · Undral Byambadalai, Tatsushi Oka, Shota Yasui

We propose a novel regression adjustment method designed for estimating distributional treatment effect parameters in randomized experiments. Randomized experiments have been extensively used to estimate treatment effect…

regressionvalid

Confidence Regions in Wasserstein Distributionally Robust Estimation

2019-06-04 · Jose Blanchet, Karthyek Murthy, Nian Si

Wasserstein distributionally robust optimization estimators are obtained as solutions of min-max problems in which the statistician selects a parameter minimizing the worst-case loss among all probability models within a…