arXiv stat.ML
· Papers
SSTQ:Privacy-Preserving Vector Quantization via Subsampled Stochastic TurboQuant
arXiv:2608.05127v1 Announce Type: cross Abstract: Achieving local differential privacy in distributed optimization while maintaining low communication cost remains challenging. Existing vector quantization methods, such as vqSGD, use high-dimensional geometric constructions but incur unfavorable dimension-dependent var