From the 1 of 7 linked papers with an AI index.
7 papers
Generalized Quadratic Gradient: A New Direction in Optimization via the Fusion of Positive-Definite Curvature Matrices and Gradients into A Unified Framework
John Chiang
Quadratic Gradient (QG) is a Newton-type optimization framework that bridges first-order gradient descent and second-order optimization by incorporating curvature information into…
Privacy-Preserving Logistic Regression Training with A Faster Gradient Variant
John Chiang
The paper proposes a quadratic gradient method to improve privacy-preserving logistic regression training, enhancing NAG, AdaGrad, and Adam and achieving fast convergence even unde…
Quasi-Quadratic Gradient: A New Direction for Accelerating the BFGS Method in Quasi-Newton Optimization
John Chiang
In this paper, we introduce the Quasi-Quadratic Gradient (QQG), a novel search direction designed to accelerate the BFGS method within the quasi-Newton framework. By defining the Q…
Volley Revolver: A Novel Matrix-Encoding Method for Privacy-Preserving Neural Networks (Inference)
John Chiang
In this work, we present a novel matrix-encoding method that is particularly convenient for neural networks to make predictions in a privacy-preserving manner using homomorphic enc…
Simplified Quadratic Gradient: A Unified Framework Bridging Gradient Descent and Newton-Type Methods by Synthesizing Hessians and Gradients
John Chiang
Accelerating the convergence of second-order optimization, particularly Newton-type methods, remains a pivotal challenge in algorithmic research. In this paper, we extend previous…
Privacy-Preserving 3-Layer Neural Network Training
John Chiang
In this manuscript, we consider the problem of privacy-preserving training of neural networks in the mere homomorphic encryption setting. We combine several exsiting techniques ava…