Counting on Dummies: Privacy Amplification with Observable Counts and Truncated Batches
[Uczenie maszynowe] Autorzy: Vitaly Feldman, Audra McMillan, Kunal Talwar
In many practical deployments of Differentially Private Stochastic Gradient Descent (DP-SGD), the server processes data in batches. Randomly sampling these batches allows for better privacy bounds via privacy amplification results. Most sampling schemes with provable privacy amplification, including Poisson sampling and random allocation, result in variable batch sizes. The privacy guarantee of these schemes requires that the batch sizes are not revealed. In distributed settings, the server performing the aggregation or any party observing the communication traffic may learn these batch sizes. Furthermore, in both centralized and distributed settings, memory and computation constraints may require each batch to be of some maximum size $s$, necessitating truncation of the batch when it exceeds this limit. It is known that this truncation can result in a significant increase in privacy lo…
- Kategoria arxiv
- cs.LG
- Kategoria
- Uczenie maszynowe