Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count% of corpus
0.3%0.5%0.8%0.1% · Oct 201919922001200920172026
2 results for “dx-privacy”
Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbationscs.LG

The paper presents a method to preserve privacy in text analysis using calibrated noise.

problem Accurately learning from user data while maintaining privacy.
method Calibrated multivariate perturbations applied to word embeddings to achieve geo-indistinguishability.
result The method provides better privacy guarantees than baseline models with minimal utility loss.
privacy-preservingtextual analysiscalibrated noiseword embeddingsdx-privacy
2019-10-20abs ↗pdf ↗
Leveraging Hierarchical Representations for Preserving Privacy and Utility in Textcs.LG

The paper proposes a privacy-preserving method for text data using Hyperbolic space.

problem Preserving user privacy in text data while maintaining utility for machine learning.
method Word representations in Hyperbolic space to provide privacy, sampling from a probability distribution.
result Demonstrates significant privacy guarantees (20x greater) compared to Euclidean space.
PrivacyHyperbolic spaceDifferential PrivacyText dataMachine Learning
2019-10-20abs ↗pdf ↗