technique
Private Stochastic Convex Optimization
techniqueactive
private-stochastic-convex-optimization-669f1dd4·1 events·first seen 1mo agoAliases: Private Stochastic Convex Optimization
Co-occurring entities
More like this (12)
Accelerated Decentralized Stochastic Gradient Descent for Strongly Convex OptimizationProximal Policy Optimizationdifferentiable convex optimizationBayesian Optimizationdistributed optimizationBiconvex OptimizationPareto Optimal Policy OptimizationDivergence Regularized Policy OptimizationDenoising Diffusion Policy Optimizationstochastic gradient ascentBayesian Multiobjective Optimizationposterior predictive variance minimization
Recent events (1)
The Privacy Price of Tail-Risk Learning: Effective Tail Sample Size in Differentially Private CVaR Optimization
This paper characterizes how differential privacy affects the statistical complexity of CVaR (Conditional Value at Risk) optimization, showing that the effective sample size governing private tail-risk learning is εnτ rather than n, where τ is the tail mass. Complete minimax rates are derived for scalar estimation and finite classes under pure DP, with lower bounds extending to approximate DP. For convex Lipschitz learning, the CVaR-specific privacy cost necessarily scales as 1/(εnτ), with dimension dependence inherited from private stochastic convex optimization. The results reduce private CVaR learning to private learning on Θ(nτ) tail records as the canonical hard subproblem.