Search Results for author:
Found 21 papers, 5 papers with code
HappyMap: A Generalized Multi-calibration Method
Fairness is captured by incorporating demographic subgroups into the class of functions~$\mathcal{C}$.
From Pseudorandomness to Multi-Group Fairness and Back
We identify and explore connections between the recent literature on multi-group fairness for prediction algorithms and the pseudorandomness notions of leakage-resilience and graph regularity.
Confidence-Ranked Reconstruction of Census Microdata from Published Statistics
Our attacks significantly outperform those that are based only on access to a public distribution or population from which the private dataset $D$ was sampled, demonstrating that they are exploiting information in the aggregate statistics $Q(D)$, and not simply the overall structure of the distribution.
Improved Generalization Guarantees in Restricted Data Models
Differential privacy is known to protect against threats to validity incurred due to adaptive, or exploratory, data analysis -- even when the analyst adversarially searches for a statistical estimate that diverges from the true value of the quantity of interest on the underlying population.
Outcome Indistinguishability
Prediction algorithms assign numbers to individuals that are popularly understood as individual "probabilities" -- what is the probability of 5-year survival after cancer diagnosis?
Interpreting Robust Optimization via Adversarial Influence Functions
Robust optimization has been widely used in nowadays data science, especially in adversarial training.
Private Post-GAN Boosting
We also provide a non-private variant of PGB that improves the data quality of standard GAN training.
Representation via Representations: Domain Generalization via Adversarially Learned Invariant Representations
We study an adversarial loss function for $k$ domains and precisely characterize its limiting behavior as $k$ grows, formalizing and proving the intuition, backed by experiments, that observing data from a larger number of domains helps.
Individual Fairness in Pipelines
It is well understood that a system built from individually fair components may not itself be individually fair.
Abstracting Fairness: Oracles, Metrics, and Interpretability
Our principal conceptual result is an extraction procedure that learns the underlying truth; moreover, the procedure can learn an approximation to this truth given access to a weak form of the oracle.
Architecture Selection via the Trade-off Between Accuracy and Robustness
We provide a general framework for characterizing the trade-off between accuracy and robustness in supervised learning.
Differentially Private False Discovery Rate Control
Differential privacy provides a rigorous framework for privacy-preserving data analysis.
Fairness Under Composition
Algorithmic fairness, and in particular the fairness of scoring and classification algorithms, has become a topic of increasing social concern and has recently witnessed an explosion of research in theoretical computer science, machine learning, statistics, the social sciences, and law.
Privacy-preserving Prediction
We demonstrate that this overhead can be avoided for the well-studied class of thresholds on a line and for a number of standard settings of convex regression.
Decoupled classifiers for fair and efficient machine learning
When it is ethical and legal to use a sensitive attribute (such as gender or race) in machine learning systems, the question remains how to do so.
Generalization in Adaptive Data Analysis and Holdout Reuse
We also formalize and address the general problem of data reuse in adaptive data analysis.
Preserving Statistical Validity in Adaptive Data Analysis
We show that, surprisingly, there is a way to estimate an exponential in $n$ number of expectations accurately even if the functions are chosen adaptively.
Analyze Gauss: Optimal Bounds for Privacy-Preserving Principal Component Analysis
We show that the well-known, but misnamed, randomized response algorithm, with properly tuned parameters, provides a nearly optimal additive quality gap compared to the best possible singular subspace of A.
Learning Fair Representations
We propose a learning algorithm for fair classification that achieves both group fairness (the proportion of members in a protected group receiving positive classification is identical to the proportion in the population as a whole), and individual fairness (similar individuals should be treated similarly).
