Search Results for author:
Found 12 papers, 0 papers with code
Harnessing large-language models to generate private synthetic text
An alternative approach, which this paper studies, is to use a sensitive dataset to generate synthetic data that is differentially private with respect to the original data, and then non-privately training a model on the synthetic data.
Private and Communication-Efficient Algorithms for Entropy Estimation
For a joint distribution over many variables whose conditional independence is given by a tree, we describe algorithms for estimating Shannon entropy that require a number of samples that is linear in the number of variables, compared to the quadratic sample complexity of prior work.
On the Pitfalls of Label Differential Privacy
We complement the negative results with a non-parametric estimator for the true privacy loss, and apply our techniques on large-scale benchmark data to demonstrate how to achieve a desired privacy protection.
Label differential privacy via clustering
We present new mechanisms for \emph{label differential privacy}, a relaxation of differentially private machine learning that only protects the privacy of the labels in the training set.
Private Optimization Without Constraint Violations
We also prove a lower bound demonstrating that the difference between the objective value of our algorithm's solution and the optimal solution is tight up to logarithmic factors among all differentially private algorithms.
Statistical Cost Sharing
We first show that when cost functions come from the family of submodular functions with bounded curvature, $\kappa$, the Shapley value can be approximated from samples up to a $\sqrt{1 - \kappa}$ factor, and that the bound is tight.
Repeated Contextual Auctions with Strategic Buyers
Motivated by real-time advertising exchanges, we analyze the problem of pricing inventory in a repeated posted-price auction.
Multi-Class Deep Boosting
We give new data-dependent learning bounds for convex ensembles in the multi-class classification setting expressed in terms of the Rademacher complexities of the sub-families composing the base classifier set, and the mixture weight assigned to each sub-family.
Learning Prices for Repeated Auctions with Strategic Buyers
Inspired by real-time ad exchanges for online display advertising, we consider the problem of inferring a buyer's value distribution for a good when the buyer is repeatedly interacting with a seller through a posted-price mechanism.
Semi-Supervised Learning with Adversarially Missing Label Information
We address the problem of semi-supervised learning in an adversarial setting.
A Reduction from Apprenticeship Learning to Classification
We provide new theoretical results for apprenticeship learning, a variant of reinforcement learning in which the true reward function is unknown, and the goal is to perform well relative to an observed expert.
Adapting to the Shifting Intent of Search Queries
Search engines today present results that are often oblivious to recent shifts in intent.
