CS 451
Data-Intensive Distributed Computing
Fall 2026
Topics
- MapReduce and Hadoop
- Cloud datacentres and dataflow abstractions
- Spark
- Language models and inverted indexes
- Parallel graph algorithms and PageRank
- Classification, gradient descent and clustering
- Data warehousing, ETL and SQL-on-Hadoop
- Column stores and Parquet
- Stream processing
- Probabilistic data structures
- Bigtable, HBase and log-structured merge trees
- Distributed hash tables and consistency trade-offs
- Bulk synchronous parallel processing
Readings
- Data-Intensive Text Processing with MapReduceChapters 1–6 across the course.
- Hadoop: The Definitive GuideSelected material from chapters 1–3 and 5–9.
- Learning SparkSelected material from chapters 1–5.
- Mathematics for Machine LearningChapters 11 and 12.
- Mining of Massive DatasetsLink Analysis, section 5.4.
- Large Language Models in Machine Translation (optional)
- Tom Mitchell — Naive Bayes and Logistic Regression (supplemental)
- MapReduce: A major step backwards
- Zaharia et al. — Discretized Streams: Fault-Tolerant Streaming Computation at Scale (SOSP 2013)
- The original Bigtable paper
- The original DHT paper
- Daniel Abadi — Consistency Tradeoffs in Modern Distributed Database System Design (Computer 45(2), 2012)
- Sherif Sakr — Large-Scale Graph Processing Systems (2016)
Sources
- Course catalogue ↗2026–2027
- course_website ↗Fall 2026