HE-DAP: Homomorphic Encryption-based Dynamic Adaptive Parameter Optimization for Statistical Computation

2026-06-09

AI Summary

This work addresses the inefficiency and accuracy trade-offs in computing inverse square roots under homomorphic encryption, which stem from fixed parameter configurations that hinder cross-platform performance. The paper presents the first environment-aware adaptive optimization framework tailored to this fundamental operation. By dynamically balancing the degree of Chebyshev polynomial approximation against the number of Newton iteration rounds, the framework automatically selects the optimal parameter configuration based on the target precision. This approach overcomes the limitations of conventional static setups, achieving up to a 2.35× speedup across Lattigo, HEaaN-CPU, and HEaaN-GPU while maintaining a relative error below 3.1×10⁻⁸, thereby substantially enhancing end-to-end statistical analysis efficiency.

Abstract

Homomorphic encryption (HE) enables privacy-preserving analytics but remains hindered by high computational overhead. We find that the inverse square root-a key primitive in many statistical and machine learning workloads-exhibits inconsistent and often suboptimal performance across HE libraries and hardware. This stems from a core trade-off between two costly HE operations: evaluating high-degree Chebyshev polynomials to speed up Newton's method versus performing bootstrapping to manage ciphertext noise. Because their relative costs vary by up to 6x across environments, any fixed configuration proves inherently inefficient. To address this challenge, we present HE-DAP, a cross-platform optimization framework that automatically navigates this trade-off. By profiling an environment's unique performance characteristics, HE-DAP finds the optimal balance between polynomial degree and iteration count to accelerate the encrypted inverse square root computation for a given accuracy target. Our evaluation on Lattigo, HEaaN-CPU, and HEaaN-GPU shows that HE-DAP's adaptive approach yields significant performance gains. It accelerates the core inverse square root computation by up to 2.35x over the fixed configuration in PP-STAT while maintaining high numerical accuracy (MRE <= 3.1 x 10^-8). We further demonstrate that optimizing this fundamental building block directly enhances the end-to-end performance of complex statistical analyses, confirming the practical benefits of our environment-aware approach. By automatically adapting to heterogeneous execution environments, HE-DAP demonstrates that principled parameter optimization can make privacy-preserving statistical analytics practical at scale.

Problem

• Homomorphic Encryption
• Inverse Square Root
• Performance Optimization
• Adaptive Parameter
• Privacy-Preserving Computation

Innovation

• Homomorphic Encryption
• Dynamic Adaptive Optimization
• Inverse Square Root
• Chebyshev Polynomials
• Bootstrapping