Engineer Readings – Telegram
[Article]
READING GROUP. PROTEAN: VM ALLOCATION SERVICE AT SCALE

This paper from Microsoft is full of technical insights into how they operate their datacenters/regions at scale. In particular, the paper discusses one of the fundamental components of any cloud provider — the VM service. The system, called Protean, is an allocation service that handles VM allocation requests

http://charap.co/reading-group-protean-vm-allocation-service-at-scale/
[Article]
Federated Quantum Machine Learning

Distributed training across several quantum computers could significantly improve the training
time and if we could share the learned model, not the data, it could potentially improve the
data privacy as the training would happen where the data is located. However, to the best of
our knowledge, no work has been done in quantum machine learning (QML) in federation setting
yet. In this work, we present the federated training on hybrid quantum-classical machine learning
models although our framework could be generalized to pure quantum machine learning model…

https://arxiv.org/pdf/2103.12010v1.pdf
[Article]
This article looks at a few approaches Amazon has taken to manage API requests to its systems to avoid overload by implementing API rate limiting (also referred to as “throttling” or "admission control”).

https://aws.amazon.com/builders-library/fairness-in-multi-tenant-systems/
Was quite impressed by this work
[Article]

Reliability Testing for Natural Language Processing Systems

https://arxiv.org/abs/2105.02590
[Book] Math for machine learning
[Article][Fraud Detection]

Graph learning methods have been extensively used in fraud detection [2] and recommendation tasks [3]. For example, at Uber Eats, a graph learning technique has been developed to surface the foods that are most likely to appeal to an individual user [4]. Graph learning is one of the ways to improve the quality and relevance of our food and restaurant recommendations on the Uber platform. A similar technology can be applied to detect collusion

https://eng.uber.com/fraud-detection/
[Article][Uber engineering][Knowledge base]
Good walkthrough how Uber eng/ml team built knowledge base with notebooks incorporated into it.
https://eng.uber.com/evolution-ds-workbench/