Understanding deep learning requires re-thinking generalization

Understanding deep learning requires re-thinking generalization Zhang et al., ICLR'17 This paper has a wonderful combination of properties: the results are easy to understand, somewhat surprising, and then leave you pondering over what it all might mean for a long while afterwards! The question the authors set out to answer was this: What is it … Continue reading Understanding deep learning requires re-thinking generalization

Neural architecture search with reinforcement learning

Neural architecture search with reinforcement learning Zoph & Le, ICLR'17 Earlier this year we looked at 'Large scale evolution of image classifiers' which used an evolutionary algorithm to guide a search for the best network architectures. In today's paper, Zoph & Le also demonstrate that learning network architectures (and also in their case recurrent cell … Continue reading Neural architecture search with reinforcement learning

CherryPick: Adaptively unearthing the best cloud configurations for big data analytics

CherryPick: Adaptively unearthing the best cloud configurations for big data analytics Alipourfard et al., NSDI'17 For big data analytics jobs, especially recurring jobs, finding a good cloud configuration (number and type of machines, CPU, memory ,disk and network options) can make a big different to overall cost and runtimes. Likewise, a poor choice can seriously … Continue reading CherryPick: Adaptively unearthing the best cloud configurations for big data analytics

vCorfu: A cloud-scale object store on a shared log

vCorfu: A cloud-scale object store on a shared log Wei et al., NSDI'17 vCorfu builds on the idea of a distributed shared log that we looked at yesterday with CORFU, to construct a distributed object store. We show that vCorfu outperforms Cassandra, a popular state-of-the-art NoSQL store, while providing strong consistency (opacity, read-own-writes), efficient transactions, … Continue reading vCorfu: A cloud-scale object store on a shared log

The design, implementation and deployment of a system to transparently compress hundreds of petabytes of image files for a file storage service

The design, implementation, and deployment of a system to transparently compress hundreds of petabytes of image files for a file storage service Horn et al., NSDI'17 When I first started reading, I thought this paper was going to be about a new compression format Dropbox had introduced for JPEG images. And it is about that, … Continue reading The design, implementation and deployment of a system to transparently compress hundreds of petabytes of image files for a file storage service

FM Backscatter: Enabling connected cities and smart fabrics

FM Backscatter: Enabling connected cities and smart fabrics Wang et al., NSDI'17 If we want to connect all the things, then we need a means of sending and/or receiving information at each thing. These transmissions require power, and no-one wants to have to plug in chargers or keep swapping batteries for endless everyday objects. So … Continue reading FM Backscatter: Enabling connected cities and smart fabrics

ViewMap: Sharing private in-vehicle dashcam videos

ViewMap: Sharing private in-vehicle dashcam videos Kim et al., NSDI'17 In the world of sensor-laden connected cars that we're rushing towards, ViewMap addresses an interesting question: how can we use the information collected by those cars for common good, without significant invasion of privacy? It raises deeper questions too about the limits of state surveillance … Continue reading ViewMap: Sharing private in-vehicle dashcam videos