Timezone: »

 
The Role of Adaptive Optimizers for Honest Private Hyperparameter Selection
Shubhankar Mohapatra · Shubhankar Mohapatra · Sajin Sasy · Gautam Kamath · Xi He · Om Dipakbhai Thakkar

Hyperparameter optimization is a ubiquitous challenge in machine learning, and the performance of a trained model depends crucially upon their effective selection. While a rich set of tools exist for this purpose, there are currently no practical hyperparameter selection methods under the constraint of differential privacy (DP). We study honest hyperparameter selection for differentially private machine learning, in which the process of hyperparameter tuning is accounted for in the overall privacy budget. To this end, we i) show that standard composition tools outperform more advanced techniques in many settings, ii) empirically and theoretically demonstrate an intrinsic connection between the learning rate and clipping norm iii) show that adaptive optimizers like DPAdam enjoy a significant advantage in the process of honest hyperparameter tuning, and iv) draw upon novel limiting behaviour of Adam in the DP setting to design a new and more efficient optimizer.

Author Information

Shubhankar Mohapatra (University of Waterloo)
Shubhankar Mohapatra (University of Waterloo)
Sajin Sasy (University of Waterloo)
Gautam Kamath (University of Waterloo)
Xi He (University of Waterloo)
Om Dipakbhai Thakkar (Google)

More from the Same Authors