Private empirical risk minimization: efficient algorithms and tight error bounds
From MaRDI portal
Cited in
(25)- Mirror descent algorithms with nearly dimension-independent rates for differentially-private stochastic saddle-point problems
- Entropic risk-averse generalized momentum methods
- Federated cubic regularized Newton learning with sparsification-amplified differential privacy
- Discovering causal structures in corrupted data: frugality in anchored Gaussian DAG models
- General Gaussian noise mechanisms and their optimality for unbiased mean estimation
- Sampling matrices from Harish-Chandra-Itzykson-Zuber densities with applications to quantum inference and differential privacy
- Tangent differential privacy
- Optimization and learning with randomly compressed gradient updates
- Efficient private SCO for heavy-tailed data via averaged clipping
- Differentially private non-convex optimization under the KL condition with optimal rates
- Differentially private regularized stochastic convex optimization with heavy-tailed data
- Private stochastic optimization with large worst-case Lipschitz parameter: optimal rates for (non-smooth) convex losses and extension to non-convex losses
- Efficient private algorithms for learning large-margin halfspaces
- Sampling without compromising accuracy in adaptive data analysis
- Private least absolute deviations with heavy-tailed data
- Estimating smooth GLM in non-interactive local differential privacy model with public unlabeled data
- Differentially private Assouad, Fano, and Le Cam
- Faster rates of private stochastic convex optimization
- Old techniques in differentially private linear regression
- Average-case information complexity of learning
- Versatile differentially private learning for general loss functions
- Personalized differential privacy for ridge regression under output perturbation
- Differentially private learning beyond the classical dimensionality regime
- Mixing times and privacy analysis for the projected Langevin algorithm under a modulus of continuity
- Revisiting differentially private stochastic convex optimization in (non)-Euclidean space
This page was built for publication: Private empirical risk minimization: efficient algorithms and tight error bounds
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6947215)
