34702 Syllabus

Textbooks

There are no official texts for the course. If you're not familiar with the background material, you may wish to look at:

Operating Systems Concepts, by Silberschatz, Galvin, and Gagne. This and the below text cover mostly background material that we assume students will be generally familiar with (both of these texts go beyond what we'll expect).
Modern Operating Systems, 2nd edition, by Andrew S. Tanenbaum.
Computer Networks: A Systems Approach, third edition, by Larry Peterson and Bruce Davie. It is available in the CMU Bookstore. Covers background networking material that we assume students will be generally familiar with.
Principles of Computer System Design: An Introduction, by Jerome H. Saltzer and M. Frans Kaashoek.
The Art of Computer Systems Performance Analysis, by Raj Jain.
Distributed Algorithms, by Nancy Lynch
Remzi Arpaci-Dusseau's OS lecture notes are a great, free, online resource for background ugrad OS concepts.

Schedule

Junchens-iMac:34702-fall20 junchenjiang$

Date	Topics	Slides (Leads)	Readings
Tue 09/29	Introduction	ppt	How to Read a Paper You and Your Research
Thu 10/01	Cloud scheduling (1)	ppt	MapReduce: Simplified Data Processing on Large Clusters CherryPick: Adaptively Unearthing the Best Cloud Configurations for Big Data Analytics*
Tue 10/06	Cloud scheduling (2)	ppt	Deep RL Tutorial Learning Scheduling Algorithms for Data Processing Clusters*
Thu 10/08	Congestion control (1)	ppt	Congestion Control for High Bandwidth-Delay Product Networks TCP ex Machina: Computer-Generated Congestion Control*
Tue 10/13	Congestion control (2)	ppt	An Experimental Study of the Learnability of Congestion Control PCC Vivace: Online-Learning Congestion Control*
Thu 10/15	CERES
Tue 10/20	Video streaming	ppt	A Buffer-Based Approach to Rate Adaptation: Evidence from a Large Video Streaming Service Neural Adaptive Video Streaming with Pensieve*
Thu 10/22	Video streaming (2)	ppt	Salsify: Low-Latency Network Video through Tighter Integration between a Video Codec and a Transport Protocol Neural Adaptive Content-aware Internet Video Delivery*
Tue 10/27	User experience	ppt	Video Stream Quality Impacts Viewer Behavior: Inferring Causality Using Quasi-Experimental Designs Developing a Predictive Model of Quality of Experience for Internet Video*
Thu 10/29	Internet-scale optimization	ppt	A Case for a Coordinated Internet Video Control Plane SPAND: Shared Passive Network Performance Discovery CFA: A Practical Prediction System for Video QoE Optimization*
Tue 11/03	Misc (1)	Neural Packet Classification (Yihua)	Learning to Route* Neural packet classification* Cellular Network Traffic Scheduling with Deep Reinforcement Learning*
Thu 11/05	Misc (2)	Learned index (Alex), AuTO (William)	The Case for Learned Index Structures* AuTO: Scaling Deep Reinforcement Learning for Datacenter-Scale Automatic Trafic Optimization* Learning Memory Access Patterns* Device Placement Optimization with Reinforcement Learning*
Tue 11/10	Counterfactual analysis	ppt	Answering what-if deployment and configuration questions with wise Harvesting Randomness to Optimize Distributed Systems*
Thu 11/12	Benchmarking	Learning in situ (Jinjin) ppt	Pantheon: the training ground for Internet congestion-control research Learning in situ: a randomized experiment in video streaming*
Tue 11/17	Control architecture and analytics	Confluo (Ted)	Libra: Divide and Conquer to Verify Forwarding Tables in Huge Networks Confluo: Distributed Monitoring and Diagnosis Stack for High-speed Networks*
Thu 11/19	Interpretability	Metis (Xun)	Cracking Open the Black Box: What Observations Can Tell Us About Reinforcement Learning Agents Interpreting Deep Learning-Based Networking Systems*
Tue 11/24	Thanksgiving
Thu 11/26	Thanksgiving
Tue 12/01	Project Presentation		TBD