REVIEW 4 cited by
A General Approach to Adding Differential Privacy to Iterative Training Procedures
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
A General Approach to Adding Differential Privacy to Iterative Training Procedures
read the original abstract
In this work we address the practical challenges of training machine learning models on privacy-sensitive datasets by introducing a modular approach that minimizes changes to training algorithms, provides a variety of configuration strategies for the privacy mechanism, and then isolates and simplifies the critical logic that computes the final privacy guarantees. A key challenge is that training algorithms often require estimating many different quantities (vectors) from the same set of examples --- for example, gradients of different layers in a deep learning architecture, as well as metrics and batch normalization parameters. Each of these may have different properties like dimensionality, magnitude, and tolerance to noise. By extending previous work on the Moments Accountant for the subsampled Gaussian mechanism, we can provide privacy for such heterogeneous sets of vectors, while also structuring the approach to minimize software engineering challenges.
Forward citations
Cited by 4 Pith papers
-
Differentially Private Two-Stage Empirical Risk Minimization with Applications to Individualized Treatment Rule
A two-stage differentially private estimator that calibrates objective-perturbation noise using stability bounds for covariate-balancing weights, demonstrated on individualized treatment rule learning.
-
Collaborative Synthetic Data Generation for Knowledge Transfer in Federated Learning
Clients encode private images through a frozen public autoencoder, compute additive class-conditional latent statistics protected by differential privacy, and the server decodes a synthetic dataset that trains competi...
-
When Determinants Are Not Enough: Private Rare Switching
Replaces determinant growth with generalized Rayleigh quotient for rare switching in private linear bandits to control worst-direction volume despite non-monotonic design matrices from noise.
-
On Optimal Hyperparameters for Differentially Private Deep Transfer Learning
Empirical study of DP transfer learning reveals that larger clipping bounds outperform under tight privacy and cumulative DP noise explains batch-size effects better than existing heuristics.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.