Papers.

SparkBench - A Spark Performance Testing Suite

Querying Time Interval Data

Feasibility of Word Difficulty Prediction

Privacy-Preserving Detection of Anomalous Phenomena in Crowdsourced Environmental Sensing

Leader Election Using NewSQL Database Systems

The Structures of Twitter Crowds and Conversations

Discussion of BigBench: A Proposed Industry Standard Performance Benchmark for Big Data

Recommender Systems in Industry: A Netflix Case Study

Practical Graph Analytics with Apache Giraph

Big Data Analytics with Spark: A Practitioner's Guide to Using Spark for Large Scale Data Analysis

Estimating user interaction strength in distributed online networks

Distributed Bayesian Learning with Stochastic Natural Gradient Expectation Propagation and the Posterior Server

This paper makes two contributions to Bayesian machine learning algorithms. Firstly, we propose stochastic natural gradient expectation propagation (SNEP), a novel alternative to expectation propagation (EP), a popular variational inference algorithm. SNEP is a black box variational algorithm, in that it does not require any simplifying assumptions on the distribution of interest, beyond the existence of some Monte Carlo sampler for estimating the moments of the EP tilted distributions. Further, as opposed to EP which has no guarantee of convergence, SNEP can be shown to be convergent, even when using Monte Carlo moment estimates. Secondly, we propose a novel architecture for distributed Bayesian learning which we call the posterior server. The posterior server allows scalable and robust Bayesian learning in cases where a data set is stored in a distributed manner across a cluster, with each compute node containing a disjoint subset of data. An independent Monte Carlo sampler is run on each compute node, with direct access only to the local data subset, but which targets an approximation to the global posterior distribution given all data across the whole cluster. This is achieved by using a distributed asynchronous implementation of SNEP to pass messages across the cluster. We demonstrate SNEP and the posterior server on distributed Bayesian learning of logistic regression and neural networks. Keywords: Distributed Learning, Large Scale Learning, Deep Learning, Bayesian Learn- ing, Variational Inference, Expectation Propagation, Stochastic Approximation, Natural Gradient, Markov chain Monte Carlo, Parameter Server, Posterior Server.

Deep Speech 2: End-to-End Speech Recognition in English and Mandarin

We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech--two vastly different languages. Because it replaces entire pipelines of hand-engineered components with neural networks, end-to-end learning allows us to handle a diverse variety of speech including noisy environments, accents and different languages. Key to our approach is our application of HPC techniques, resulting in a 7x speedup over our previous system. Because of this efficiency, experiments that previously took weeks now run in days. This enables us to iterate more quickly to identify superior architectures and algorithms. As a result, in several cases, our system is competitive with the transcription of human workers when benchmarked on standard datasets. Finally, using a technique called Batch Dispatch with GPUs in the data center, we show that our system can be inexpensively deployed in an online setting, delivering low latency when serving users at scale.

Survey of robust and resilient social media tools on Android

Embarrassingly Parallel Time Series Analysis for Large Scale Weak Memory Systems

Autonomous smartphone apps: self-compilation, mutation, and viral spreading

Asynchronous Complex Analytics in a Distributed Dataflow Architecture

SPRIGHT: A Fast and Robust Framework for Sparse Walsh-Hadamard Transform

We consider the problem of computing the Walsh-Hadamard Transform (WHT) of some $N$-length input vector in the presence of noise, where the $N$-point Walsh spectrum is $K$-sparse with $K = {O}(N^{\delta})$ scaling sub-linearly in the input dimension $N$ for some $0<\delta<1$. Over the past decade, there has been a resurgence in research related to the computation of Discrete Fourier Transform (DFT) for some length-$N$ input signal that has a $K$-sparse Fourier spectrum. In particular, through a sparse-graph code design, our earlier work on the Fast Fourier Aliasing-based Sparse Transform (FFAST) algorithm computes the $K$-sparse DFT in time ${O}(K\log K)$ by taking ${O}(K)$ noiseless samples. Inspired by the coding-theoretic design framework, Scheibler et al. proposed the Sparse Fast Hadamard Transform (SparseFHT) algorithm that elegantly computes the $K$-sparse WHT in the absence of noise using ${O}(K\log N)$ samples in time ${O}(K\log^2 N)$. However, the SparseFHT algorithm explicitly exploits the noiseless nature of the problem, and is not equipped to deal with scenarios where the observations are corrupted by noise. Therefore, a question of critical interest is whether this coding-theoretic framework can be made robust to noise. Further, if the answer is yes, what is the extra price that needs to be paid for being robust to noise? In this paper, we show, quite interestingly, that there is {\it no extra price} that needs to be paid for being robust to noise other than a constant factor. In other words, we can maintain the same sample complexity ${O}(K\log N)$ and the computational complexity ${O}(K\log^2 N)$ as those of the noiseless case, using our SParse Robust Iterative Graph-based Hadamard Transform (SPRIGHT) algorithm.

A survey of P2P multidimensional indexing structures

Performance analysis of a Tor-like onion routing implementation

Ask Me Anything: Dynamic Memory Networks for Natural Language Processing

Most tasks in natural language processing can be cast into question answering (QA) problems over language input. We introduce the dynamic memory network (DMN), a neural network architecture which processes input sequences and questions, forms episodic memories, and generates relevant answers. Questions trigger an iterative attention process which allows the model to condition its attention on the inputs and the result of previous iterations. These results are then reasoned over in a hierarchical recurrent sequence model to generate answers. The DMN can be trained end-to-end and obtains state-of-the-art results on several types of tasks and datasets: question answering (Facebook's bAbI dataset), text classification for sentiment analysis (Stanford Sentiment Treebank) and sequence modeling for part-of-speech tagging (WSJ-PTB). The training for these different tasks relies exclusively on trained word vector representations and input-question-answer triplets.

Linear Types Can Change the Blockchain

Finding Intermediary Topics Between People of Opposing Views: A Case Study

Anonymous online purchases with exhaustive operational security

MLlib: Machine Learning in Apache Spark

Apache Spark is a popular open-source platform for large-scale data processing that is well-suited for iterative machine learning tasks. In this paper we present MLlib, Spark's open-source distributed machine learning library. MLlib provides efficient functionality for a wide range of learning settings and includes several underlying statistical, optimization, and linear algebra primitives. Shipped with Spark, MLlib supports several languages and provides a high-level API that leverages Spark's rich ecosystem to simplify the development of end-to-end machine learning pipelines. MLlib has experienced a rapid growth due to its vibrant open-source community of over 140 contributors, and includes extensive documentation to support further growth and to let users quickly get up to speed.

Estimation from Pairwise Comparisons: Sharp Minimax Bounds with Topology Dependence

Data in the form of pairwise comparisons arises in many domains, including preference elicitation, sporting competitions, and peer grading among others. We consider parametric ordinal models for such pairwise comparison data involving a latent vector w* e Rd that represents the "qualities" of the d items being compared; this class of models includes the two most widely used parametric models|the Bradley-Terry-Luce (BTL) and the Thurstone models. Working within a standard minimax framework, we provide tight upper and lower bounds on the optimal error in estimating the quality score vector w* under this class of models. The bounds depend on the topology of the comparison graph induced by the subset of pairs being compared, via the spectrum of the Laplacian of the comparison graph. Thus, in settings where the subset of pairs may be chosen, our results provide principled guidelines for making this choice. Finally, we compare these error rates to those under cardinal measurement models and show that the error rates in the ordinal and cardinal settings have identical scalings apart from constant pre-factors.

Higher category models of the pi-calculus

A Self-Compiling Android Data Obfuscation Tool

Workforce Issues: Profiles of Specialty Crop Farms in New York State

Wisdom of Crowds or Wisdom of a Few

Why are deep nets reversible: A simple theory, with implications for training.

Watching Fictive Motion in Action: Discourse Data from the TV News Archive

Violence Metaphors in Presidential Debates

Traversal Query Language For Scala.Meta

The Missing Piece in Complex Analytics: Low Latency, Scalable Model Management and Serving with Velox

The Lake-dwellings of Europe

The Case for Invariant-Based Concurrency Control.

Sum-of-Squares Lower Bounds for Sparse PCA.

Succinct: Enabling Queries on Compressed Data

Style Checking With Scala.Meta

Streaming@Twitter

Simple, Efficient, and Neural Algorithms for Sparse Coding.

SEEDB: Efficient Data-Driven Visualization Recommendations to Support Visual Analytics

Scalable Transactions for Scalable Distributed Database Systems

sbt in Action

Robust Sparse Walsh-Hadamard Transform : The SPRIGHT Algorithm

Remote patient monitoring to improve health: challenges and opportunities

Region-based off-heap memory for Scala

This work explores support for region-based memory in Scala through macro-based domain-specific encoding that exploits a number of extensible language features such as implicits and value classes.

Refinements in Syntactic Parsing

Random Walks on Context Spaces: Towards an Explanation of the Mysteries of Semantic Word Embeddings.