Research map / Optimization / Nonconvex and smooth optimization
Optimal Query Complexity of Secure Stochastic Convex Optimization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Require learner privacy in addition to optimization accuracy | Stochastic convex optimization · Secure stochastic convex optimization | query complexity: an additional factor of \Theta(1/\delta^{\rm adv}) | Hurt |
| Mix uniformly distributed queries with an efficient confidential optimization strategy | Secure learning protocol · Secure stochastic convex optimization | function error: \tilde{\mathcal{O}}\big((T\delta^{\rm adv})^{-\frac{\kappa}{2\kappa - 2}}\big) | Helped |
| Mix uniformly distributed queries with an efficient confidential optimization strategy | Secure learning protocol · Secure stochastic convex optimization | point error: \tilde{\mathcal{O}}\big((T\delta^{\rm adv})^{-\frac{1}{2\kappa - 2}}\big) | Helped |
| Use a noisy sign oracle rather than a noiseless sign oracle | Secure binary search · Secure noisy binary search | secure query complexity lower bound: \Omega\left(\frac{1-\delta}{\delta^{\rm adv} c(p)}\log({\varepsilon}^{\rm adv} /{\varepsilon})\right) | Hurt |
Closest papers by meaning
- Faster Algorithms for User-Level Private Stochastic Convex Optimization (NeurIPS 2024 · similarity 0.89)
- Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions (NeurIPS 2024 · similarity 0.88)
- Information Complexity of Stochastic Convex Optimization: Applications to Generalization, Memorization, and Tracing (ICML 2024 · similarity 0.88)
- On Traceability in $\ell_p$ Stochastic Convex Optimization (NeurIPS 2025 · similarity 0.87)
- Differential Private Stochastic Optimization with Heavy-tailed Data: Towards Optimal Rates (AAAI 2025 · similarity 0.87)
- Improved Differentially Private and Lazy Online Convex Optimization: Lower Regret without Smoothness Requirements (ICML 2024 · similarity 0.87)
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.