Locally Private Inference for Riemannian Stochastic Optimization
arXiv:2609.22642v1 Announce Type: new Abstract: We develop inference for manifold-valued population minimizers when each observation belongs to a different participant and only locally private messages reach the analyst. The method releases randomized tangent gradients and combines them through Rie…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-09-22 04:00 · arXiv stat.ML
Locally Private Inference for Riemannian Stochastic Optimization