DeepAI AI Chat
Log In Sign Up

Optimal minimization of the covariance loss

by   Vishesh Jain, et al.

Let X be a random vector valued in ℝ^m such that X_2≤ 1 almost surely. For every k≥ 3, we show that there exists a sigma algebra ℱ generated by a partition of ℝ^m into k sets such that Cov(X) - Cov(𝔼[X|ℱ]) _F≲1/√(logk). This is optimal up to the implicit constant and improves on a previous bound due to Boedihardjo, Strohmer, and Vershynin. Our proof provides an efficient algorithm for constructing ℱ and leads to improved accuracy guarantees for k-anonymous or differentially private synthetic data. We also establish a connection between the above problem of minimizing the covariance loss and the pinning lemma from statistical physics, providing an alternate (and much simpler) algorithmic proof in the important case when X ∈{± 1}^m/√(m) almost surely.


page 1

page 2

page 3

page 4


Algorithmically Effective Differentially Private Synthetic Data

We present a highly effective algorithmic approach for generating ε-diff...

Covariance loss, Szemeredi regularity, and differential privacy

We show how randomized rounding based on Grothendieck's identity can be ...

Differentially private low-dimensional representation of high-dimensional data

Differentially private synthetic data provide a powerful mechanism to en...

Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling

Recent work of Erlingsson, Feldman, Mironov, Raghunathan, Talwar, and Th...

Differentially private inference via noisy optimization

We propose a general optimization-based framework for computing differen...

Posterior covariance information criterion for arbitrary loss functions

We propose a novel computationally low-cost method for estimating the pr...

Even Simpler Deterministic Matrix Sketching

This paper provides a one-line proof of Frequent Directions (FD) for ske...