Beyond Square Roots: A Memory-Efficient Explicit Factorization for Multi-Epoch Private Learning

arXiv:2605.18379 · cs.LG · Submitted 2026-05-18 · Read on arXiv

cs.LG

Submitted: 2026-05-18

Updated: 2026-09-26

Terminology

• Accuracy — 26× in this paper · explained in 1 episode
• Differential Privacy — 20× in this paper · explained in 4 episodes
• Differentially Private — 16× in this paper · explained in 3 episodes
• Banded Inverse Square Root — 5× in this paper
• Generalization — 4× in this paper · explained in 13 episodes
• In International Conference on Machine Learning — 4× in this paper
• Root Mean Squared Error — 4× in this paper
• Aggregation — 3× in this paper · explained in 1 episode
• Theoretical Guarantees — 3× in this paper · explained in 2 episodes
• Banded Square Root — 2× in this paper
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• In Foundations of Responsible Computing — 2× in this paper
• In International Conference on Learning Representations — 2× in this paper
• Bayesian Optimization — 1× in this paper · explained in 3 episodes
• Buffered Linear Toeplitz — 1× in this paper
• Calibration — 1× in this paper · explained in 7 episodes
• Core — 1× in this paper · explained in 2 episodes
• Federated Learning — 1× in this paper · explained in 14 episodes
• International Conference on Very Large Data Bases — 1× in this paper
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Binned Group Algebra Factorization for Differentially Private Continual Counting
• DP- lambda CGD: Efficient Noise Correlation for Differentially Private Model Training
• JAX-Privacy: A library for differentially private machine learning
• Correlated Noise Mechanisms for Differentially Private Learning
• Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks