Privacy constraints in regularized convex optimization

نویسندگان

  • Kamalika Chaudhuri
  • Anand D. Sarwate
چکیده

Privacy concerns are becoming more important as more personal data moves online. It is therefore of interest to develop versions of data-processing algorithms which can be guaranteed to preserve the privacy of individuals’ data. A general method for creating a privacy-preserving version of a convex optimization problem is described, along with applications to machine learning, statistics, and resource allocation problems.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Linearized Alternating Direction Method of Multipliers for Constrained Nonconvex Regularized Optimization

In this paper, we consider a wide class of constrained nonconvex regularized minimization problems, where the constraints are linearly constraints. It was reported in the literature that nonconvex regularization usually yields a solution with more desirable sparse structural properties beyond convex ones. However, it is not easy to obtain the proximal mapping associated with nonconvex regulariz...

متن کامل

Privacy-preserving logistic regression

This paper addresses the important tradeoff between privacy and learnability, when designing algorithms for learning from private databases. We focus on privacy-preserving logistic regression. First we apply an idea of Dwork et al. [6] to design a privacy-preserving logistic regression algorithm. This involves bounding the sensitivity of regularized logistic regression, and perturbing the learn...

متن کامل

An accelerated proximal gradient algorithm for nuclear norm regularized least squares problems

The affine rank minimization problem, which consists of finding a matrix of minimum rank subject to linear equality constraints, has been proposed in many areas of engineering and science. A specific rank minimization problem is the matrix completion problem, in which we wish to recover a (low-rank) data matrix from incomplete samples of its entries. A recent convex relaxation of the rank minim...

متن کامل

On Second-order Properties of the Moreau-Yosida Regularization for Constrained Nonsmooth Convex Programs

In this paper, we attempt to investigate a class of constrained nonsmooth convex optimization problems, that is, piecewise C2 convex objectives with smooth convex inequality constraints. By using the Moreau-Yosida regularization, we convert these problems into unconstrained smooth convex programs. Then, we investigate the second-order properties of the Moreau-Yosida regularization η. By introdu...

متن کامل

Characterization of Properly Efficient Solutions for Convex Multiobjective Programming with Nondifferentiable vanishing constraints

This paper studies the convex multiobjective optimization problem with vanishing constraints‎. ‎We introduce a new constraint qualification for these problems‎, ‎and then a necessary optimality condition for properly efficient solutions is presented‎. ‎Finally by imposing some assumptions‎, ‎we show that our necessary condition is also sufficient for proper efficiency‎. ‎Our results are formula...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • CoRR

دوره abs/0907.1413  شماره 

صفحات  -

تاریخ انتشار 2009