Equivalent Class Optimization (EC-Opt)
It has been widely observed that many activation functions and pooling methods of neural network models have (positive-) rescaling-invariant property, including ReLU, PReLU, max-pooling, and average pooling, which makes fully-connected neural networks (FNNs) and convolutional neural networks (CNNs) invariant to (positive) rescaling operation across layers. This may cause unneglectable problems with their optimization: (1) different NN models could be equivalent, but their gradients can be very different from each other; (2) it can be proven that the loss functions may have many spurious critical points in the redundant weight space. To tackle these problems, in this paper, we first characterize the rescaling-invariant properties of NN models using equivalent classes and prove that the dimension of the equivalent class space is significantly smaller than the dimension of the original weight space. Then we represent the loss function in the compact equivalent class space and develop novel algorithms that conduct optimization of the NN models directly in the equivalent class space. We call these algorithms Equivalent Class Optimization (abbreviated as EC-Opt) algorithms. Moreover, we design efficient tricks to compute the gradients in the equivalent class, which almost have no extra computational complexity as compared to standard back-propagation (BP). We conducted experimental study to demonstrate the effectiveness of our proposed new optimization algorithms. In particular, we show that by using the idea of EC-Opt, we can significantly improve the accuracy of the learned model (for both FNN and CNN), as compared to using conventional stochastic gradient descent algorithms. …

Cyber-All-Intel
Keeping up with threat intelligence is a must for a security analyst today. There is a volume of information present in `the wild’ that affects an organization. We need to develop an artificial intelligence system that scours the intelligence sources, to keep the analyst updated about various threats that pose a risk to her organization. A security analyst who is better `tapped in’ can be more effective. In this paper we present, Cyber-All-Intel an artificial intelligence system to aid a security analyst. It is a system for knowledge extraction, representation and analytics in an end-to-end pipeline grounded in the cybersecurity informatics domain. It uses multiple knowledge representations like, vector spaces and knowledge graphs in a ‘VKG structure’ to store incoming intelligence. The system also uses neural network models to pro-actively improve its knowledge. We have also created a query engine and an alert system that can be used by an analyst to find actionable cybersecurity insights. …

Group-Fused Graphical Lasso (GFGL)
We consider the consistency properties of a regularised estimator for the simultaneous identification of both changepoints and graphical dependency structure in multivariate time-series. Traditionally, estimation of Gaussian Graphical Models (GGM) is performed in an i.i.d setting. More recently, such models have been extended to allow for changes in the distribution, but only where changepoints are known a-priori. In this work, we study the Group-Fused Graphical Lasso (GFGL) which penalises partial-correlations with an L1 penalty while simultaneously inducing block-wise smoothness over time to detect multiple changepoints. We present a proof of consistency for the estimator, both in terms of changepoints, and the structure of the graphical models in each segment. …

Preconditioned Stochastic Gradient Descent (PSGD)
This paper studies the performance of preconditioned stochastic gradient descent (PSGD), which can be regarded as an enhance stochastic Newton method with the ability to handle gradient noise and non-convexity at the same time. We have improved the implementation of PSGD, unrevealed its relationship to equilibrated stochastic gradient descent (ESGD) and batch normalization, and provided a software package (https://…/psgd_tf ) implemented in Tensorflow to compare variations of PSGD and stochastic gradient descent (SGD) on a wide range of benchmark problems with commonly used neural network models, e.g., convolutional and recurrent neural networks. Comparison results clearly demonstrate the advantages of PSGD in terms of convergence speeds and generalization performances. …