1BOneBench

Search OneBench

Search signals, briefings, benchmarks and glossary terms.

Back to Signals
RESEARCHMonitorNEXT 12 MONTHS

Quadratic Objective Perturbation: Curvature-Based Differential Privacy

arXiv cs.LG — Machine Learning

Factual evidence

What the source reports

Research proposes Quadratic Objective Perturbation (QOP) for differentially private empirical risk minimization, addressing limitations of Linear Objective Perturbation (LOP) with unbounded gradients.

Open source