Search Results for author:
Found 8 papers, 3 papers with code
Privacy-Preserving 3-Layer Neural Network Training using Mere Homomorphic Encryption Technique
In this manuscript, we consider the problem of privacy-preserving training of neural networks in the mere homomorphic encryption setting.
Activation Functions Not To Active: A Plausible Theory on Interpreting Neural Networks
This $\textit{ Super Space }$ is something like a coordinate system, in which every multivalue function can be represented by a $\textit{ Super Plane }$.
Privacy-Preserving CNN Training with Transfer Learning
; and (4) we use a simple but flexible matrix-encoding method named $\texttt{Volley Revolver}$ to manage the data flow in the ciphertexts, which is the key factor to complete the whole homomorphic CNN training.
Quadratic Gradient: Combining Gradient Algorithms and Newton's Method as One
Also, Chiang speculates that there might be a relation between the Hessian matrix and the learning rate for the first-order gradient descent method.
Multinomial Logistic Regression Algorithms via Quadratic Gradient
A recently work proposed a faster gradient called $\texttt{quadratic gradient}$ that can accelerate the binary logistic regression training, and presented an enhanced Nesterov's accelerated gradient (NAG) method for binary logistic regression.
Volley Revolver: A Novel Matrix-Encoding Method for Privacy-Preserving Neural Networks (Inference)
In a public cloud with 40 vCPUs, our convolutional neural network implementation on the MNIST testing dataset takes $\sim$ 287 seconds to compute ten likelihoods of 32 encrypted images of size $28 \times 28$ simultaneously.
On Polynomial Approximation of Activation Function
In this work, we propose an interesting method that aims to approximate an activation function over some domain by polynomials of the presupposing low degree.
Privacy-Preserving Logistic Regression Training with A Faster Gradient Variant
In this paper, we propose a faster gradient variant called $\texttt{quadratic gradient}$ for privacy-preserving logistic regression training.
