arXiv subjects

Xiao Zeng

Publications and source records attributed to Xiao Zeng.

22 records · Page 2Linked to original sources

arXiv2020

Deep Learning in the Era of Edge Computing: Challenges and Opportunities

The era of edge computing has arrived. Although the Internet is the backbone of edge computing, its true value lies at the intersection of gathering data from sensors and extracting meaningful information from the sensor data. We envision that in the near future, majority of edge devices will be equipped with machine intelligence powered by deep learning. However, deep learning-based approaches require a large volume of high-quality data to train and are very expensive in terms of computation, memory, and power consumption. In this chapter, we describe eight research challenges and promising opportunities at the intersection of computer systems, networking, and machine learning. Solving those challenges will enable resource-limited edge devices to leverage the amazing capability of deep learning. We hope this chapter could inspire new research that will eventually lead to the realization of the vision of intelligent edge.

cs.LG↗

arXiv2020

Computing the Number of Equivalent Classes on $\mathcal{R}(s,n)/\mathcal{R}(k,n)$

Affine equivalent classes of Boolean functions have many applications in modern cryptography and circuit design. Previous publications have shown that affine equivalence on the entire space of Boolean functions can be computed up to 10 variables, but not on the quotient Boolean function space modulo functions of different degrees. Computing the number of equivalent classes of cosets of Reed-Muller code $\mathcal{R}(1,n)$ is equivalent to classifying Boolean functions modulo linear functions, which can be computed only when $n\leq 7$. Based on the linear representation of the affine group $\mathcal{AGL}(n,2)$ on $\mathcal{R}(s,n)/\mathcal{R}(k,n)$, we obtain a useful counting formula to compute the number of equivalent classes. Instead of computing the conjugate classes and representatives directly in $\mathcal{AGL}(n,2)$, we reduce the computation complexity by introducing an isomorphic permutation group $P_n$ and performing the computation in $P_n$. With the proposed algorithm, the number of equivalent classes of cosets of $R(1,n)$ can be computed up to 10 variables. Furthermore, the number of equivalent classes on $\mathcal{R}(s,n)/\mathcal{R}(k,n)$ can also be computed when $-1\leq k< s\leq n\leq 10$, which is a major improvement and advancement comparing to previous methods.

cs.IT↗

arXiv2019

HM-NAS: Efficient Neural Architecture Search via Hierarchical Masking

The use of automatic methods, often referred to as Neural Architecture Search (NAS), in designing neural network architectures has recently drawn considerable attention. In this work, we present an efficient NAS approach, named HM- NAS, that generalizes existing weight sharing based NAS approaches. Existing weight sharing based NAS approaches still adopt hand-designed heuristics to generate architecture candidates. As a consequence, the space of architecture candidates is constrained in a subset of all possible architectures, making the architecture search results sub-optimal. HM-NAS addresses this limitation via two innovations. First, HM-NAS incorporates a multi-level architecture encoding scheme to enable searching for more flexible network architectures. Second, it discards the hand-designed heuristics and incorporates a hierarchical masking scheme that automatically learns and determines the optimal architecture. Compared to state-of-the-art weight sharing based approaches, HM-NAS is able to achieve better architecture search performance and competitive model evaluation accuracy. Without the constraint imposed by the hand-designed heuristics, our searched networks contain more flexible and meaningful architectures that existing weight sharing based NAS approaches are not able to discover.

cs.LG↗

arXiv2018

NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Vision

Mobile vision systems such as smartphones, drones, and augmented-reality headsets are revolutionizing our lives. These systems usually run multiple applications concurrently and their available resources at runtime are dynamic due to events such as starting new applications, closing existing applications, and application priority changes. In this paper, we present NestDNN, a framework that takes the dynamics of runtime resources into account to enable resource-aware multi-tenant on-device deep learning for mobile vision systems. NestDNN enables each deep learning model to offer flexible resource-accuracy trade-offs. At runtime, it dynamically selects the optimal resource-accuracy trade-off for each deep learning model to fit the model's resource demand to the system's available runtime resources. In doing so, NestDNN efficiently utilizes the limited resources in mobile vision systems to jointly maximize the performance of all the concurrently running applications. Our experiments show that compared to the resource-agnostic status quo approach, NestDNN achieves as much as 4.2% increase in inference accuracy, 2.0x increase in video frame processing rate and 1.7x reduction on energy consumption.

cs.CV↗