SOSP '23 | The Case for Collaboration by Margo Seltzer скачать в хорошем качестве

SOSP '23 | The Case for Collaboration by Margo Seltzer

Margo Seltzer, Canada 150 Chair in Computer Systems The Case for Collaboration (Everything a Systems Person really needs to know about Machine Learning) It's 2023, and the answer to every system performance or optimization problem is "machine learning." But what kinds of models are appropriate for these applications? I'm going to try to convince you that, as in good system design, "simpler is better." And, in this case, simpler has many benefits: simpler models are typically more efficient in both space and time, they are frequently transparently interpretable, and they produce accuracy and generalization equivalent to the fanciest deep learning model you can build. Presented at SOSP 2023 https://sosp2023.mpi-sws.org in Koblenz, Germany