Xi Wu, Matthew Fredrikson, Wentao Wu, Somesh Jha, Jeffrey F. Naughton
Add an identifier
Abstract:Private regression has received attention from both database and security
communities. Recent work by Fredrikson et al. (USENIX Security 2014) analyzed
the functional mechanism (Zhang et al. VLDB 2012) for training linear
regression models over medical data. Unfortunately, they found that model
accuracy is already unacceptable with differential privacy when $\varepsilon =
5$. We address this issue, presenting an explicit connection between
differential privacy and stable learning theory through which a ...
Use a distibution that's symmetric around the origin and normalize the results so they lie on the sphere. E.g. you can use a Gaussian. Here's some code.
def sample_sphere_uniformly(d, n_samples):
"""Sample uniformly from d-sphere.
d: dimension of sphere
n: number of sample points to generate
array of shape (n, d+1)
import numpy as np
x = np.random.normal(0, 1, (n_samples, d+1))
return x / np.linalg.norm(x, axis=1, keepdims=True)