MARVEL: Enabling Mobile Augmented Reality with Low Energy and Low Latency

Hyung-Sin Kim Intelligent, Real-Time, Systems

This paper presents MARVEL, a mobile augmented reality (MAR) system which provides a notation display service with imperceptible latency (<100 ms) and low energy consumption on regular mobile devices. In contrast to conventional MAR systems, which recognize objects using image-based computations performed in the cloud, MARVEL mainly utilizes a mobile device’s local inertial sensors for recognizing and tracking multiple objects, while computing local optical flow and offloading images only when necessary. We propose a system architecture which uses local inertial tracking, local optical flow, and visual tracking in the cloud synergistically. On top of that, we investigate how to minimize the overhead for image computation and offloading. We have implemented and deployed a holistic prototype system in a commercial building …

Authors: Kaifei Chen, Tong Li, Hyung-Sin Kim, David Culler, Randy Katz

Random Projection Design for Scalable Implicit Smoothing of Randomly Observed Stochastic Processes

Aaditya Ramdas Intelligent, Statistical Methodology, Theoretical ML

Standard methods for multi-variate time series analysis are hampered by sampling at random timestamps, long range dependencies , and the scale of the data. In this paper we present a novel estimator for cross-covariance of randomly observed time series which identifies the dynamics of an unobserved stochastic process. We analyze the statistical properties of our estimator without the assumption that observation timestamps are independent from the process of interest and show that our solution does not suffer from the corresponding issues affecting standard estimators for cross-covariance. We implement and evaluate our statistically sound and scalable approach in the distributed setting using Apache Spark and demonstrate its ability to identify interactions between processes on simulations and financial data with tens of millions of samples. Pdf: Aistats_camera_ready

Authors: , Joseph Gonzalez, Evan Sparks, Alexandre M. Bayen

Clipper: A Low-Latency Online Prediction Serving System

Daniel Crankshaw Intelligent, Real-Time, Systems

Machine learning is being deployed in a growing number of applications which demand real-time, accurate, and robust predictions under heavy query load. However, most machine learning frameworks and systems only address model training and not deployment. In this paper, we introduce Clipper, a general-purpose low-latency prediction serving system. Interposing between end-user applications and a wide range of machine learning frameworks, Clipper introduces a modular architecture to simplify model deployment across frameworks and applications. Furthermore, by introducing caching, batching, and adaptive model selection techniques, Clipper reduces prediction latency and improves prediction throughput, accuracy, and robustness without modifying the underlying machine learning frameworks. We evaluate Clipper on four common machine learning benchmark datasets and demonstrate its ability to meet the latency, accuracy, …

Authors: Dan Crankshaw, Xin Wang, Giulio Zhou, Michael J. Franklin, Joseph Gonzalez, Ion Stoica