Learning Rate Scheduling with Matrix Factorization for Private Training
By: Nikita P. Kalinin, Joel Daniel Andersson
Potential Business Impact:
Makes private computer learning more accurate.
We study differentially private model training with stochastic gradient descent under learning rate scheduling and correlated noise. Although correlated noise, in particular via matrix factorizations, has been shown to improve accuracy, prior theoretical work focused primarily on the prefix-sum workload. That workload assumes a constant learning rate, whereas in practice learning rate schedules are widely used to accelerate training and improve convergence. We close this gap by deriving general upper and lower bounds for a broad class of learning rate schedules in both single- and multi-epoch settings. Building on these results, we propose a learning-rate-aware factorization that achieves improvements over prefix-sum factorizations under both MaxSE and MeanSE error metrics. Our theoretical analysis yields memory-efficient constructions suitable for practical deployment, and experiments on CIFAR-10 and IMDB datasets confirm that schedule-aware factorizations improve accuracy in private training.
Similar Papers
Understanding Incremental Learning with Closed-form Solution to Gradient Flow on Overparamerterized Matrix Factorization
Machine Learning (CS)
Teaches computers to learn things step-by-step.
Inductive Bias and Spectral Properties of Single-Head Attention in High Dimensions
Machine Learning (Stat)
Helps AI learn better by understanding how it works.
Global Convergence of Four-Layer Matrix Factorization under Random Initialization
Optimization and Control
Makes deep computer learning work better.