Research map / Federated learning and privacy / Differential privacy
A Framework for Private Matrix Analysis in Sliding Window Model
Jalaj Upadhyay, Sarvagya Upadhyay
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use approximate spectral histogram property instead of exact spectral histogram for maintaining PSD matrices | sliding window private spectral approximation · sliding window private matrix analysis | robustness to privacy noise / accuracy | Improved |
| Naively adding a PSD noise matrix or Apriv-style storage of per-window sanitized matrices | private spectral approximation · sliding window | space | Hurt |
| Adding the spectral histogram algorithm of Braverman et al. with scaled noise | sliding window spectral approximation under privacy · sliding window | accuracy under privacy noise | Hurt |
| Use sublinear-space sub-window continual release instead of binary tree over the window | continual release variant · sliding window | space vs error | Mixed |
| Private projection preserving summary (projection to k/η dimensions) instead of naive spectral approximation for PCA | private PCA · sliding window PCA | additive error | Improved |
Closest papers by meaning
- An Iterative Algorithm for Differentially Private $k$-PCA with Adaptive Noise (NeurIPS 2025 · similarity 0.90)
- On Differentially Private Subspace Estimation in a Distribution-Free Setting (NeurIPS 2024 · similarity 0.88)
- Spectral Perturbation Bounds for Low-Rank Approximation with Applications to Privacy (NeurIPS 2025 · similarity 0.87)
- Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation (NeurIPS 2026 · similarity 0.87)
- On the Computational Complexity of Private High-dimensional Model Selection (NeurIPS 2024 · similarity 0.87)
- A Private Approximation of the 2nd-Moment Matrix of Any Subsamplable Input (NeurIPS 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
