Scalable Distributed Nonnegative Matrix Factorization with Block-Wise Updates - 2018


Nonnegative Matrix Factorization (NMF) has been applied with nice success on a big selection of applications. As NMF is increasingly applied to massive datasets like internet-scale dyadic information, it's desirable to leverage a cluster of machines to store those datasets and to hurry up the factorization method. But, it's difficult to efficiently implement NMF in an exceedingly distributed setting. During this Project, we show that by leveraging a replacement form of update functions, we can perform local aggregation and fully explore parallelism. Thus, the new kind is much additional efficient than the traditional type in distributed implementations. Moreover, below the new type of update functions, we will perform frequent updates and lazy updates, which aim to use the foremost recently updated data whenever possible and avoid unnecessary computations. Thus, frequent updates and lazy updates are a lot of efficient than their ancient concurrent counterparts. Through a series of experiments on a local cluster also because the Amazon EC2 cloud, we tend to demonstrate that our implementations with frequent updates or lazy updates are up to two orders of magnitude faster than the prevailing implementation with the ancient type of update functions.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE : Measuring Fitness and Precision of Automatically Discovered Process Models: A Principled and Scalable Approach ABSTRACT: We are able to generate a process model by using automated process discovery techniques,
PROJECT TITLE : Scalable and Practical Natural Gradient for Large-Scale Deep Learning ABSTRACT: Because of the increase in the effective mini-batch size, the generalization performance of the models produced by large-scale distributed
PROJECT TITLE : On Model Selection for Scalable Time Series Forecasting in Transport Networks ABSTRACT: When it comes to short-term traffic predictions, up to the scale of one hour, the transport literature is quite extensive;
PROJECT TITLE : PPD: A Scalable and Efficient Parallel Primal-Dual Coordinate Descent Algorithm ABSTRACT: One of the most common approaches to optimization is called Dual Coordinate Descent, or DCD for short. Due to the sequential
PROJECT TITLE : On-Device Scalable Image-Based Localization via Prioritized Cascade Search and Fast One-Many RANSAC ABSTRACT: We describe a complete on-device solution for large-scale image-based urban localisation. Compact image

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry