• Corpus ID: 14305556

Private Convex Empirical Risk Minimization and High-dimensional Regression

@inproceedings{Kifer2012PrivateCE,
  title={Private Convex Empirical Risk Minimization and High-dimensional Regression},
  author={Daniel Kifer and Adam D. Smith and Abhradeep Thakurta},
  booktitle={Annual Conference Computational Learning Theory},
  year={2012}
}
We consider differentially private algorithms for convex empirical risk minimization (ERM. [] Key Method To this end: (a) We significantly extend the analysis of the “objective perturbation” algorithm of Chaudhuri et al. (2011) for convex ERM problems. We show that their method can be modified to use less noise (be more accurate), and to apply to problems with hard constraints and non-differentiable regularizers. We also give a tighter, data-dependent analysis of the additional error introduced by their…

Tables from this paper

(Near) Dimension Independent Risk Bounds for Differentially Private Learning

This paper shows that under certain assumptions, variants of both output and objective perturbation algorithms have no explicit dependence on p; the excess risk depends only on the L2-norm of the true risk minimizer and that of training points.

Efficient Private Empirical Risk Minimization for High-dimensional Learning

This paper theoretically study the problem of differentially private empirical risk minimization in the projected subspace (compressed domain) of ERM problems, and shows that for the class of generalized linear functions, given only the projected data and the projection matrix, excess risk bounds can be obtained.

Differentially Private Empirical Risk Minimization with Sparsity-Inducing Norms

This is the first work that analyzes the dual optimization problems of risk minimization problems in the context of differential privacy with a particular class of convex but non-smooth regularizers that induce structured sparsity and loss functions for generalized linear models.

Non-Euclidean Differentially Private Stochastic Convex Optimization

Differentially private (DP) stochastic convex optimization (SCO) is a fundamental problem, where the goal is to approximately minimize the population risk with respect to a convex loss function,

Private Non-smooth Empirical Risk Minimization and Stochastic Convex Optimization in Subquadratic Steps

This work gets a (nearly) optimal bound on the excess empirical risk and excess population loss with subquadratic gradient complexity on the differentially private Empirical Risk Minimization and Stochastic Convex Optimization problems for non-smooth convex functions.

Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds

This work provides new algorithms and matching lower bounds for differentially private convex empirical risk minimization assuming only that each data point's contribution to the loss function is Lipschitz and that the domain of optimization is bounded.

Private Stochastic Convex Optimization: Optimal Rates in 𝓁1 Geometry

The upper bound is based on a new algorithm that combines the iterative localization approach of Feldman et al. (2020a) with a new analysis of private regularized mirror descent and is achieved by a new variance-reduced version of the Frank-Wolfe algorithm that requires just a single pass over the data.

On Differentially Private Stochastic Convex Optimization with Heavy-tailed Data

This paper proposes a method based on the sample-and-aggregate framework, which has an excess population risk of $\tilde{O}(\frac{d^3}{n\epsilon^4})$ (after omitting other factors), and provides a gradient smoothing and trimming based scheme to achieve excess population risks.

Evading the Curse of Dimensionality in Unconstrained Private GLMs

It is shown that for unconstrained convex generalized linear models (GLMs), one can obtain an excess empirical risk of Õ (√ rank/εn ) , where rank is the rank of the feature matrix in the GLM problem, n is the number of data samples, and ε is the privacy parameter.

Noninteractive Locally Private Learning of Linear Models via Polynomial Approximations

This work considers differentially private algorithms that operate in the local model, where each data record is stored on a separate user device and randomization is performed locally by those devices.
...

References

SHOWING 1-10 OF 26 REFERENCES

Differentially Private Empirical Risk Minimization

This work proposes a new method, objective perturbation, for privacy-preserving machine learning algorithm design, and shows that both theoretically and empirically, this method is superior to the previous state-of-the-art, output perturbations, in managing the inherent tradeoff between privacy and learning performance.

Stochastic Convex Optimization

Stochastic convex optimization is studied, and it is shown that the key ingredient is strong convexity and regularization, which is only a sufficient, but not necessary, condition for meaningful non-trivial learnability.

Privacy-preserving statistical estimation with optimal convergence rates

It is shown that for a large class of statistical estimators T and input distributions P, there is a differentially private estimator AT with the same asymptotic distribution as T, which implies that AT (X) is essentially as good as the original statistic T(X) for statistical inference, for sufficiently large samples.

Calibrating Noise to Sensitivity in Private Data Analysis

The study is extended to general functions f, proving that privacy can be preserved by calibrating the standard deviation of the noise according to the sensitivity of the function f, which is the amount that any single argument to f can change its output.

A unified framework for high-dimensional analysis of $M$-estimators with decomposable regularizers

A unified framework for establishing consistency and convergence rates for regularized M-estimators under high-dimensional scaling is provided and one main theorem is state and shown how it can be used to re-derive several existing results, and also to obtain several new results.

Smooth sensitivity and sampling in private data analysis

This is the first formal analysis of the effect of instance-based noise in the context of data privacy, and shows how to do this efficiently for several different functions, including the median and the cost of the minimum spanning tree.

Mechanism Design via Differential Privacy

It is shown that the recent notion of differential privacv, in addition to its own intrinsic virtue, can ensure that participants have limited effect on the outcome of the mechanism, and as a consequence have limited incentive to lie.

ℓâ‚€-norm Minimization for Basis Selection

A sparse Bayesian learning-based method of minimizing the l0-norm while reducing the number of troublesome local minima is demonstrated and it is demonstrated that there are typically many fewer for general problems of interest.

Composition attacks and auxiliary information in data privacy

This paper investigates composition attacks, in which an adversary uses independent anonymized releases to breach privacy, and provides a precise formulation of this property, and proves that an important class of relaxations of differential privacy also satisfy the property.

No free lunch in data privacy

This paper argues that privacy of an individual is preserved when it is possible to limit the inference of an attacker about the participation of the individual in the data generating process, different from limiting the inference about the presence of a tuple.