Sharding the shards: managing datastore locality at scale with Akkio

Sharding the shards: managing datastore locality at scale with Akkio Annamalai et al., OSDI’18 In Harry Potter, the Accio Summoning Charm summons an object to the caster of the spell, sometim… | Continue reading


@blog.acolyer.org | 5 years ago

An interesting/influential/important paper from the world of CS every morning

an interesting/influential/important paper from the world of CS every weekday morning, as selected by Adrian Colyer | Continue reading


@blog.acolyer.org | 6 years ago

The FuzzyLog: a partially ordered shared log

The FuzzyLog: a partially ordered shared log Lockerman et al., OSDI’18 If you want to build a distributed system then having a distributed shared log as an abstraction to build upon — one tha… | Continue reading


@blog.acolyer.org | 6 years ago

Moment-based quantile sketches for efficient high cardinality aggregation query

Moment-based quantile sketches for efficient high cardinality aggregation queries Gan et al., VLDB’18 Today we’re temporarily pausing our tour through some of the OSDI’18 papers in order to l… | Continue reading


@blog.acolyer.org | 6 years ago

The Mornging Paper – Out of the Tar Pit (2015)

Out of the Tar Pit – Moseley & Marks 2006 This is the final Desert Island Paper choice from Jonas Bonér, and a great way to round out the week. ‘Out of the Tar Pit’ was the 10… | Continue reading


@blog.acolyer.org | 6 years ago

Noria: dynamic, partially-stateful data-flow for high-performance web apps

Noria: dynamic, partially-stateful data-flow for high-performance web applications Gjengset, Schwarzkopf et al., OSDI’18 I have way more margin notes for this paper than I typically do, and t… | Continue reading


@blog.acolyer.org | 6 years ago

RobinHood: dynamic reallocation from cache-rich to cache-poor

RobinHood: tail latency aware caching – dynamic reallocation from cache-rich to cache-poor Berger et al., OSDI’18 It’s time to rethink everything you thought you knew about caching! My … | Continue reading


@blog.acolyer.org | 6 years ago

RobinHood: tail latency aware caching – dynamic reallocation

RobinHood: tail latency aware caching – dynamic reallocation from cache-rich to cache-poor Berger et al., OSDI’18 It’s time to rethink everything you thought you knew about caching! My … | Continue reading


@blog.acolyer.org | 6 years ago

Maelstrom: mitigating datacenter-level disasters by draining traffic

Maelstrom: mitigating datacenter-level disasters by draining interdependent traffic safely and efficiently Veeraraghavan et al., OSDI’18 Here’s a really valuable paper detailing four plus yea… | Continue reading


@blog.acolyer.org | 6 years ago

Maelstrom

Maelstrom: mitigating datacenter-level disasters by draining interdependent traffic safely and efficiently Veeraraghavan et al., OSDI’18 Here’s a really valuable paper detailing four plus yea… | Continue reading


@blog.acolyer.org | 6 years ago

LegoOS: a disseminated, distributed OS for hardware resource disaggregation

LegoOS: a disseminated, distributed OS for hardware resource disaggregation Shan et al., OSDI’18 One of the interesting trends in hardware is the proliferation and importance of dedicated acc… | Continue reading


@blog.acolyer.org | 6 years ago

Orca: differential bug localization in large-scale services – the morning paper

Orca: differential bug localization in large-scale services Bhagwan et al., OSDI’18 Earlier this week we looked at REPT, the reverse debugging tool deployed live in the Windows Error Reportin… | Continue reading


@blog.acolyer.org | 6 years ago

REPT: reverse debugging of failures in deployed software

REPT: reverse debugging of failures in deployed software Cui et al., OSDI’18 REPT (‘repeat’) won a best paper award at OSDI’18 this month. It addresses the problem of debugging crashes in pro… | Continue reading


@blog.acolyer.org | 6 years ago

Capturing and enhancing in situ system observability for failure detection

Capturing and enhancing in situ system observability for failure detection Huang et al., OSDI’18 The central idea in this paper is simple and brilliant. The place where we have the most relev… | Continue reading


@blog.acolyer.org | 6 years ago

Is Sound Gradual Typing Dead?

Is Sound Gradual Typing Dead? – Takikawa et al. 2016 Last year we looked at the notion of gradual typing in an ECOOP 2015 paper by Takikawa et al. based on TypedRacket. Today’s choice f… | Continue reading


@blog.acolyer.org | 6 years ago

Automatic discovery of tactics in spatio-temporal soccer match data

Automatic discovery of tactics in spatio-temporal soccer match data Decroos et al., KDD’18 Here’s a fun paper to end the week. Data collection from sporting events is now widespread. This fue… | Continue reading


@blog.acolyer.org | 6 years ago

Detecting spacecraft anomalies using LSTMs

Detecting spacecraft anomalies using LSTMs and nonparametric dynamic thresholding Hundman et al., KDD’18 How do you effectively monitor a spacecraft? That was the question facing NASA’s Jet P… | Continue reading


@blog.acolyer.org | 6 years ago

Online parameter selection for web-based ranking problems

Online parameter selection for web-based ranking problems Agarwal et al., KDD’18 Last week we looked at production systems from Facebook, Airbnb, and Snap Inc., today it’s the turned of Linke… | Continue reading


@blog.acolyer.org | 6 years ago

X

I know you’ll be back: interpretable new user clustering and churn prediction on a mobile social application Yang et al., KDD’18 Churn rates (how fast users abandon your app / service) are re… | Continue reading


@blog.acolyer.org | 6 years ago

Customized regression model for Airbnb dynamic pricing

Customized regression model for Airbnb dynamic pricing Ye et al., KDD’18 This paper details the methods that Airbnb use to suggest prices to listing hosts (hosts ultimately remain in control … | Continue reading


@blog.acolyer.org | 6 years ago

Customized regression model for Airbnb dynamic pricing

Customized regression model for Airbnb dynamic pricing Ye et al., KDD’18 This paper details the methods that Airbnb use to suggest prices to listing hosts (hosts ultimately remain in control … | Continue reading


@blog.acolyer.org | 6 years ago

Rosetta: large scale system for text detection and recognition in images

Rosetta: large scale system for text detection and recognition in images Borisyuk et al., KDD’18 Rosetta is Facebook’s production system for extracting text (OCR) from uploaded images. In the… | Continue reading


@blog.acolyer.org | 6 years ago

Rosetta: large scale system for text detection and recognition in images

Rosetta: large scale system for text detection and recognition in images Borisyuk et al., KDD’18 Rosetta is Facebook’s production system for extracting text (OCR) from uploaded images. In the… | Continue reading


@blog.acolyer.org | 6 years ago

Columnstore and B+ tree – are hybrid physical designs important?

Columnstore and B+ tree – are hybrid physical designs important? Dziedzic et al., SIGMOD’18 Earlier this week we looked at the design of column stores and their advantages for analytic … | Continue reading


@blog.acolyer.org | 6 years ago

The design and implementation of modern column-oriented database systems

The design and implementation of modern column-oriented database systems Abadi et al., Foundations and trends in databases, 2012 I came here by following the references in the Smoke paper we looked… | Continue reading


@blog.acolyer.org | 6 years ago

Smoke: fine-grained lineage at interactive speed

Smoke: fine-grained lineage at interactive speed Psallidas et al., VLDB’18 Data lineage connects the input and output data items of a computation. Given a set of output records, a backward li… | Continue reading


@blog.acolyer.org | 6 years ago

Same-different problems strain convolutional neural networks

Same-different problems strain convolutional neural networks Ricci et al., arXiv 2018 Since we’ve been looking at the idea of adding structured representations and relational reasoning to deep lear… | Continue reading


@blog.acolyer.org | 6 years ago

Relational inductive biases, deep learning, and graph networks

Relational inductive biases, deep learning, and graph networks Battaglia et al., arXiv’18 Earlier this week we saw the argument that causal reasoning (where most of the interesting questions … | Continue reading


@blog.acolyer.org | 6 years ago

Why Functional Programming Matters

Why Functional Programming Matters John Hughes, Research Topics in Functional Programming, 1990 (based on an earlier Computer Journal paper that appeared in 1989). 1989/1990 must have been a fairly… | Continue reading


@blog.acolyer.org | 6 years ago

The seven tools of causal inference with reflections on machine learning

The seven tools of causal inference with reflections on machine learning Pearl, CACM 2018 With thanks to @osmandros for sending me a link to this paper on twitter. In this technical report Judea Pe… | Continue reading


@blog.acolyer.org | 6 years ago

An empirical analysis of anonymity in Zcash

An empirical analysis of anonymity in Zcash Kappos et al., USENIX Security’18 As we’ve seen before, in practice Bitcoin offers little in the way of anonymity. Zcash on the other hand was care… | Continue reading


@blog.acolyer.org | 6 years ago

QSYM: a practical concolic execution engine tailored for hybrid fuzzing

QSYM: a practical concolic execution engine tailored for hybrid fuzzing Yun et al., USENIX Security 2018 There are two main approaches to automated test case generated for uncovering bugs and vulne… | Continue reading


@blog.acolyer.org | 6 years ago

Quantifying FB exploitation of sensitive personal data for advertising purpose

Unveiling and quantifying Facebook exploitation of sensitive personal data for advertising purposes Cabañas et al., USENIX Security 2018 Earlier this week we saw how the determined can still bypas… | Continue reading


@blog.acolyer.org | 6 years ago

A comprehensive evaluation of third-party cookie policies

Who left open the cookie jar? A comprehensive evaluation of third-party cookie policies from the Franken et al., USENIX Security 2018 This paper won a ‘Distinguished paper’ award at USENIX Security… | Continue reading


@blog.acolyer.org | 6 years ago

Fear the reaper: characterization and fast detection of card skimmers

Fear the reaper: characterization and fast detection of card skimmers Scaife et al., USENIX Security 2018 Until I can get my hands on a Skim Reaper I’m not sure I’ll ever trust an ATM or other expo… | Continue reading


@blog.acolyer.org | 6 years ago

Fear the reaper: characterization and fast detection of card skimmers

Fear the reaper: characterization and fast detection of card skimmers Scaife et al., USENIX Security 2018 Until I can get my hands on a Skim Reaper I’m not sure I’ll ever trust an ATM or other expo… | Continue reading


@blog.acolyer.org | 6 years ago

STTR: A system for tracking all vehicles all the time at the edge of the network

STTR: A system for tracking all vehicles all the time at the edge of the network Xu et al., DEBS’18 With apologies for only bringing you two paper write-ups this week: we moved house, which t… | Continue reading


@blog.acolyer.org | 6 years ago

Learning the structure of generative models without labeled data

Learning the structure of generative models without labeled data Bach et al., ICML’17 For the last couple of posts we’ve been looking at Snorkel and BabbleLabble which both depend on data pro… | Continue reading


@blog.acolyer.org | 6 years ago

The morning paper: Training classifiers with natural language explanations

Training classifiers with natural language explanations Hancock et al., ACL’18 We looked at Snorkel earlier this week, which demonstrates that maybe AI isn’t going to take over all of our pro… | Continue reading


@blog.acolyer.org | 6 years ago

Snorkel: rapid training data creation with weak supervision

Snorkel: rapid training data creation with weak supervision Ratner et al., VLDB’18 Earlier this week we looked at Sparser, which comes from the Stanford Dawn project, “a five-year resea… | Continue reading


@blog.acolyer.org | 6 years ago

Filter before you parse: faster analytics on raw data with Sparser

Filter before you parse: faster analytics on raw data with Sparser Palkar et al., VLDB’18 We’ve been parsing JSON for over 15 years. So it’s surprising and wonderful that with a fresh look at… | Continue reading


@blog.acolyer.org | 6 years ago

Fairness without demographics in repeated loss minimization

Fairness without demographics in repeated loss minimization Hashimoto et al., ICML’18 When we train machine learning models and optimise for average loss it is possible to obtain systems with… | Continue reading


@blog.acolyer.org | 6 years ago

Human-Robot Team for Rescue Mission:Team ViGIR at 2013 Darpa Robotics Challenge

Human-Robot Teaming for Rescue Missions: Team ViGIR’s Approach to the 2013 DARPA Robotics Challenge Trials – Kohlbrecher et al. 2014 Yesterday we looked at ROS, the Robot Operating Syst… | Continue reading


@blog.acolyer.org | 6 years ago

Obfuscatd gradients give false sense of sec:circmventin defense to advrsarial ex

Obfuscated gradients give a false sense of security: circumventing defenses to adversarial examples Athalye et al., ICML’18 There has been a lot of back and forth in the research community on… | Continue reading


@blog.acolyer.org | 6 years ago

Delayed impact of fair machine learning

Delayed impact of fair machine learning Liu et al., ICML’18 “Delayed impact of fair machine learning” won a best paper award at ICML this year. It’s not an easy read (at least it … | Continue reading


@blog.acolyer.org | 6 years ago

Bounding data races in space and time – part II

Bounding data races in space and time Dolan et al., PLDI’18 Yesterday we looked at the case for memory models supporting local data-race-freedom (local DRF). In today’s post we’ll push deeper… | Continue reading


@blog.acolyer.org | 6 years ago

Bounding data races in space and time – part I

Bounding data races in space and time Dolan et al., PLDI’18 Are you happy with your programming language’s memory model? In this beautifully written paper, Dolan et al. point out some of the … | Continue reading


@blog.acolyer.org | 6 years ago

HHVM JIT: A profile-guided, region-based compiler for PHP and Hack

HHVM JIT: A profile-guided, region-based compiler for PHP and Hack Ottoni, PLDI’18 HHVM is a virtual machine for PHP and Hack (a PHP extension) which is used to power Facebook’s website among… | Continue reading


@blog.acolyer.org | 6 years ago