This research provides insights for the separation of cryptocurrencies from other assets. Using dimensionality reduction techniques, we show that most of the variation among cryptocurrencies, stocks, exchange rates, commodities, bonds, and real estate indexes can be explained by the tail, memory and moment factors of their log-returns. By applying various classification methods, cryptocurrencies are categorized as a separate asset class, mainly due to the tail factor. The main result is the complete separation of cryptocurrencies from the other asset types, using the Maximum Variance Components Split method. Additionally, we show that cryptocurrencies tend to exhibit similar characteristics over time and become more distinguished from other asset classes (synchronic evolution).

Recently sparse representation has been applied to visual tracker by modeling the target appearance using a sparse approximation over a template set, which leads to the so-called L_1 trackers as it needs to solve an ℓ_1 norm related minimization problem for many times. While these L_1 trackers showed impressive tracking accuracies, they are very computationally demanding and the speed bottleneck is the solver to ℓ_1 norm minimizations. This paper aims at developing an L_1 tracker that not only runs in real time but also enjoys better robustness than other L_1 trackers. In our proposed L_1 tracker, a new ℓ_1 norm related minimization model is proposed to improve the tracking accuracy by adding an ℓ_1 norm regularization on the coefficients associated with the trivial templates. Moreover, based on the accelerated proximal gradient approach, a very fast numerical solver is developed to solve the resulting ℓ_1 norm related minimization problem with guaranteed quadratic convergence. The great running time efficiency and tracking accuracy of the proposed tracker is validated with a comprehensive evaluation involving eight challenging sequences and five alternative state-of-the-art trackers.

Convolutional neural networks have been widely deployed in various application scenarios. In order to extend the applications’ boundaries to some accuracy-crucial domains, researchers have been investigating approaches to boost accuracy through either deeper or wider network structures, which brings with them the exponential increment of the computational and storage cost, delaying the responding time. In this paper, we propose a general training framework named self distillation, which notably enhances the performance (accuracy) of convolutional neural networks through shrinking the size of the network rather than aggrandizing it. Different from traditional knowledge distillation - a knowledge transformation methodology among networks, which forces student neural networks to approximate the softmax layer outputs of pre-trained teacher neural networks, the proposed self distillation framework distills knowledge within network itself. The networks are firstly divided into several sections. Then the knowledge in the deeper portion of the networks is squeezed into the shallow ones. Experiments further prove the generalization of the proposed self distillation framework: enhancement of accuracy at average level is 2.65%, varying from 0.61% in ResNeXt as minimum to 4.07% in VGG19 as maximum. In addition, it can also provide flexibility of depth-wise scalable inference on resource-limited edge devices. Our codes have been released on github. https://github.com/ArchipLab-LinfengZhang/ pytorch-self-distillation.

Remarkable achievements have been attained by deep neural networks in various applications. However, the increasing depth and width of such models also lead to explosive growth in both storage and computation, which has restricted the deployment of deep neural networks on resource-limited edge devices. To address this problem, we propose the so-called SCAN framework for networks training and inference, which is orthogonal and complementary to existing acceleration and compression methods. The proposed SCAN firstly divides neural networks into multiple sections according to their depth and constructs shallow classifiers upon the intermediate features of different sections. Moreover, attention modules and knowledge distillation are utilized to enhance the accuracy of shallow classifiers. Based on this architecture, we further propose a threshold controlled scalable inference mechanism to approach human-like sample-specific inference. Experimental results show that SCAN can be easily equipped on various neural networks without any adjustment on hyper-parameters or neural networks architectures, yielding significant performance gain on CIFAR100 and ImageNet. Codes are be released on https://github.com/ArchipLab-LinfengZhang/pytorch-scalable-neural-networks.

Feature distillation, a primary method in knowledge distillation, always leads to significant accuracy improvements. Most existing methods distill features in the teacher network through a manually designed transformation. In this paper, we propose a novel distillation method named task-oriented feature distillation (TOFD) where the transformation is convolutional layers that are trained in a data-driven manner by task loss. As a result, the task-oriented information in the features can be captured and distilled to students. Moreover, an orthogonal loss is applied to the feature resizing layer in TOFD to improve the performance of knowledge distillation. Experiments show that TOFD outperforms other distillation methods by a large margin on both image classification and 3D classification tasks. Codes have been released in Github[3].