DeepAI
Log In Sign Up

Empirical Risk Minimization in the Non-interactive Local Model of Differential Privacy

11/11/2020
by   Di Wang, et al.
0

In this paper, we study the Empirical Risk Minimization (ERM) problem in the non-interactive Local Differential Privacy (LDP) model. Previous research on this problem <cit.> indicates that the sample complexity, to achieve error α, needs to be exponentially depending on the dimensionality p for general loss functions. In this paper, we make two attempts to resolve this issue by investigating conditions on the loss functions that allow us to remove such a limit. In our first attempt, we show that if the loss function is (∞, T)-smooth, by using the Bernstein polynomial approximation we can avoid the exponential dependency in the term of α. We then propose player-efficient algorithms with 1-bit communication complexity and O(1) computation cost for each player. The error bound of these algorithms is asymptotically the same as the original one. With some additional assumptions, we also give an algorithm which is more efficient for the server. In our second attempt, we show that for any 1-Lipschitz generalized linear convex loss function, there is an (ϵ, δ)-LDP algorithm whose sample complexity for achieving error α is only linear in the dimensionality p. Our results use a polynomial of inner product approximation technique. Finally, motivated by the idea of using polynomial approximation and based on different types of polynomial approximations, we propose (efficient) non-interactive locally differentially private algorithms for learning the set of k-way marginal queries and the set of smooth queries.

READ FULL TEXT

page 1

page 2

page 3

page 4

02/12/2018

Efficient Empirical Risk Minimization with Smooth Loss Functions in Non-interactive Local Differential Privacy

In this paper, we study the Empirical Risk Minimization problem in the n...
05/27/2014

Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds

In this paper, we initiate a systematic investigation of differentially ...
10/01/2019

Estimating Smooth GLM in Non-interactive Local Differential Privacy Model with Public Unlabeled Data

In this paper, we study the problem of estimating smooth Generalized Lin...
11/20/2014

Private Empirical Risk Minimization Beyond the Worst Case: The Effect of the Constraint Set Geometry

Empirical Risk Minimization (ERM) is a standard technique in machine lea...
02/20/2020

Input Perturbation: A New Paradigm between Central and Local Differential Privacy

Traditionally, there are two models on differential privacy: the central...
09/17/2022

On PAC Learning Halfspaces in Non-interactive Local Privacy Model with Public Unlabeled Data

In this paper, we study the problem of PAC learning halfspaces in the no...