Recycling Scraps: Improving Private Learning by Leveraging Intermediate Checkpoints. (arXiv:2210.01864v1 [cs.LG])

All state-of-the-art (SOTA) differentially private machine learning (DP ML)
methods are iterative in nature, and their privacy analyses allow publicly
releasing the intermediate training checkpoints. However, DP ML benchmarks, and
even practical deployments, typically use only the final training checkpoint to
make predictions. In this work, for the first time, we comprehensively explore
various methods that aggregate intermediate checkpoints to improve the utility
of DP training. Empirically, we demonstrate that checkpoint aggregations
provide significant gains in the prediction accuracy over …

arxiv recycling