Search Results for author:
Found 5 papers, 0 papers with code
DP-SGD for non-decomposable objective functions
To overcome this issue, we develop a new DP-SGD variant for similarity based loss functions -- in particular the commonly used contrastive loss -- that manipulates gradients of the objective function in a novel way to obtain a senstivity of the summed gradient that is $O(1)$ for batch size $n$.
Duff: A Dataset-Distance-Based Utility Function Family for the Exponential Mechanism
Given a particular dataset and a statistic (e. g., median, mode), this function family assigns utility to a possible output o based on the number of individuals whose data would have to be added to or removed from the dataset in order for the statistic to take on value o.
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.
Online Learning for Non-Stationary A/B Tests
The rollout of new versions of a feature in modern applications is a manual multi-stage process, as the feature is released to ever larger groups of users, while its performance is carefully monitored.
Revenue Optimization with Approximate Bid Predictions
In the context of advertising auctions, finding good reserve prices is a notoriously challenging learning problem.
