Class Time and Place: TF 2:00pm - 3:20pm, Location: Sage 4203
Instructor: Stacy Patterson     sep AT cs.rpi.edu
Office Hours: T 3:30pm - 4:30pm or by appointment Please email me to arrange an online meeting.

A message from Prof. Stewart, Head of the CS Department, about the switch to online instruction due to the COVID-19 outbreak

Course Syllabus

Intro Slides

Schedule

In this course, we will study significant tools, applications, and algorithms at the frontiers of cloud computing, edge computing, and the Internet of Things. The course content will come directly from research papers, articles, and documentation of cloud and edge architectures and technologies. We will work together to develop a deep understanding of this content through class presentations and discussions of this material. Students will also create a research project of their choosing.

CSCI-4510/6510: Distributed Systems and Algorithms

The pre-requisite may be replaced by suitable background and coursework in network programming and distributed systems. Undergraduates who are interested in taking this class should contact the instructor for permission.

• How to read a paper, S. Keshav.
• How NOT to review a paper, G. Cormode.
• Example Summary for E-Paxos paper

You must submit three paper reviews. You can select any papers from the paper list below, provided you are not the presenter of the paper. Reviews must be submitted (emailed to the professor) before the corresponding paper is presented in class.

Paper reviews consist of a short summary of the paper, a list of three strong points, and a least of three weak points. A an example summary for the E-Paxos paper can be found here.

The due dates for reviews are as follows:

Review 1: due by March 6, 2020, end of day

Review 2: due at least 7 days after you submit Review 1 and at least 7 days before you submit Review 3

Review 3: due before class on April 7, 2020

Your project report must be 4 to 6 pages, in IEEE conference format. The report template can be found here.

Updated project deadlines

Meeting to select project topic: March 6, 2020

Initial list of references: March 17, 2020 March 24, 2020, end of day (by email)

Project status report: March 20, 2020 March 27, 2020 (in class)

Final project presentations: Last two weeks of class

Project report: April 29, 2020

Replication and Storage Systems

1. There is more consensus in Egalitarian parliaments, Moraru, Andersen, and Kaminsky, SOSP 2013.
2. Just Say NO to Paxos Overhead: Replacing Consensus with Network Ordering, Li, Michael, Sharma, Szekeres, and Ports, OSDI 2016.
3. Low-Latency Multi-Datacenter Databases using Replicated Commit, Mahmoud, Nawab, Pucher, Agrawal, and El Abbadi, VLDB 2013.
4. vCorfu: A Cloud-Scale Object Store on a Shared Log, Wei, et al., NSDI 2017.
5. ALOHA-KV: high performance read-only and write-only distributed transactions, Fan, Golab, and Morrey, SoCC 2017.

Streaming Systems

1. Drizzle: Fast and Adaptable Stream Processing at Scale, Venkataraman, Panda, Ousterhout, Armbrust, Ghodsi, Franklin, Recht, and Stoica, SoSP 2017.
2. ApproxIoT: Approximate Analytics for Edge Computing, Wen, Quoc, Bhatotia, Chen, and Lee, ICDCS 2018.

Federated Learning

1. Communication-Efficient Learning of Deep Networks from Decentralized Data, McMahan, Moore, Ramage, Hampson, and Aguera y Arcas, 2017.
2. Federated Learning for Mobile Keyboard Prediction, Hard, Rao, Mathews, Ramaswamy, Beaufays, Augentstein, Eichner, Kiddon, and Ramage, 2018.
3. Towards Federated Learning at Scale: System Design, Bonawitz, et al, 2019.
4. Federated Learning: Strategies for Improving Communication Efficiency,Konecny, McMahan, Yu, Richtarik, Suresh, and Bacon, 2017
5. How To Backdoor Federated Learning, Bagdasaryan, Veit, Hua, Estrin, and Shmatikov, 2018.
6. Expanding the Reach of Federated Learning by Reducing Client Resource Requirements, Caldas, Konecny, McMahan, and Talwakar, 2019.
7. Federated Learning over Wireless Networks: Optimization Model Design and Analysis, Tran, Bao, Zomaya, Nguyen, and Hong, 2019.

Privacy

• Geo-Indistinguishability: Differential Privacy for Location-Based Systems, Andres, Bordenabe, Chatzikokolakis, and Palamidessi, CCS 2013.
• Not just privacy: Improving performance of private deep learning in mobile cloud, Wang, Zhang, BZao, Zhu, Cao, and Yu, KDD 2018.

Miscellaneous

• Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent, Peva Blanchard, El Mahdi El Mhamdi, Rachid Guerraoui, and Julien Stainer, NIPS, 2017.
• Aegean: replication beyond the client-server model, Remzi Can Aksoy and Manos Kapritsos, SOSP, 2019.
• Structure-less content-based routing in mobile ad hoc networks, R. Baldoni, R. Beraldi, G. Cugola, M. Migliavacca, and L. Querzoni, ICPS, 2005.
• Fault-Tolerance, Fast and Slow: Exploiting Failure Asynchrony in Distributed Systems, Ramnatthan Alagappan, Aishwarya Ganesan, Jing Liu, Andrea Arpaci-DusseaRu, and Remzi Arpaci-Dusseau, OSDI, 2018.