Next-generation data-parallel dataflow systems
Prof. Frank McSherry,
ETH Zurich –
The Naiad project at Microsoft Research introduced a new model of dataflow computation, timely dataflow, which was designed to support low-latency computation in data-parallel dataflow graphs containing structured cycles. This model substantially enlarged the space of data-parallel computations that can be reasonably expressed, as compared to other modern “big data” systems. Naiad achieved excellent performance it its intended application domains, largely by providing the dataflow operators with meaningful and low-overhead coordination primitives, but otherwise staying out of their way.
In this talk we will discuss performance issues with existing systems, review timely dataflow, and present a new data-parallel design that coordinates less frequently yet more accurately. The design is largely implemented, written in 100% safe Rust and available at https://github.com/frankmcsherry/timely-dataflow, and currently out-performs several popular distributed systems even when run on the speaker’s laptop.
This talk reflects work done jointly with Derek Murray, Rebecca Isaacs, Michael Isard, Paul Barham, and Martin Abadi. The photo credit is due to Mihai Budiu.
Frank McSherry is currently visiting ETH Zurich, and is formerly affiliated with Microsoft Research, Silicon Valley. While there he led the Naiad project, which introduced both differential and timely dataflow, and remains one of the top-performing big data platforms. He also works with differential privacy, due in part to its interesting relationship to data-parallel computation. Frank currently enjoys spending his time in places other than Silicon Valley.
Rodrigo Seromenho Miragaia Rodrigues
IST Alameda, anfiteatro EA3
Mathematics, Physics & Machine Learning Seminar Series (Online)
The Mathematics, Physics & Machine Learning seminar series takes place until July 16, between 17:30 and 18:30, via Zoom.
The seminars aims to bring together mathematicians and physicists interested in machine learning (ML) with ML and AI experts interested in mathematics and physics, with the goals of introducing innovative Mathematics and Physics-inspired techniques in Machine Learning and, reciprocally, applying Machine Learning to problems in Mathematics and Physics.
Attendance is free but registration is required.
More information and the next seminars available here.
40 Years of Science and Knowledge: Empowering Companies to Face New Challenges
The first session to celebrate INESC 40th years, also associated with INESC TEC 35th anniversary, will take place on July 6, at 2:30 pm, at the Faculty of Engineering, University of Porto.
This session will be transmitted by Zoom Webinar.
Opening session: José Manuel Mendonça, President of INESC TEC and Professor at FEUP
Keynote speech: Elisa Ferreira, European Commissioner for Cohesion and Reforms
Moderator: Manuel Carvalho, Director of PÚBLICO
António Amorim, President & CEO of Corticeira Amorim
António Mexia, President of EDP
Isabel Furtado, CEO of TMG Automotive and president of COTEC
Manuel Carlos, President of APICCAPS
Paulo Azevedo, Chairman of the board of directors of SONAE
José Manuel Tribolet, President of INESC
António Costa, Prime Minister (to confirm)
The event is free, but a registration is required in order to receive a link.
LxMLS 2020 – 10th Lisbon Machine Learning School
The 10th edition of Lisbon Machine Learning School, LxMLS, will take place from July 21st to July 29th at Instituto Superior Técnico (IST).
This event is organized by IST, Instituto de Telecomunicações (IT), INESC-ID, Unbabel, and Priberam Labs.
Applications until March 15th. For more information and to apply, access here.