Ryan Marcus, assistant professor at the University of Pennsylvania. Using machine learning to build the next generation of data systems.

    ____                       __  ___
   / __ \__  ______ _____     /  |/  /___ _____________  _______
  / /_/ / / / / __ `/ __ \   / /|_/ / __ `/ ___/ ___/ / / / ___/
 / _, _/ /_/ / /_/ / / / /  / /  / / /_/ / /  / /__/ /_/ (__  )
/_/ |_|\__, /\__,_/_/ /_/  /_/  /_/\__,_/_/   \___/\__,_/____/
      /____/

   ___                   __  ___
  / _ \__ _____ ____    /  |/  /__ ___________ _____
 / , _/ // / _ `/ _ \  / /|_/ / _ `/ __/ __/ // (_-<
/_/|_|\_, /\_,_/_//_/ /_/  /_/\_,_/_/  \__/\_,_/___/
     /___/

   ___  __  ___
  / _ \/  |/  /__ ___________ _____
 / , _/ /|_/ / _ `/ __/ __/ // (_-<
/_/|_/_/  /_/\_,_/_/  \__/\_,_/___/

CIS 6500, Fall 2025

Lecture slides

CIS 6500 Readings

Part 1: Intro & Demo Seminar

Sept 24 — The Case for a Learned Sorting Algorithm (SIGMOD ’20)

Part 2: Rows and Columns

Sept 29 — Column-Stores vs. Row-Stores: How Different Are They Really? (SIGMOD ’08)
Oct 1 — Integrating Compression and Execution in Column-Oriented Database Systems (SIGMOD ’06)

Part 3: Execution Models

Part 4: Index Structures

Oct 13 — B-Tree Indexes and CPU Caches (ICDE ’01)
Oct 15 — Column Sketches: A Scan Accelerator for Rapid and Robust Predicate Evaluation (SIGMOD ’18)
Oct 20 — The Case for Learned Index Structures (SIGMOD ’18)
- Benchmarking Learned Indexes (VLDB ’21)
Oct 22 — Learning Multi-Dimensional Indexes (SIGMOD ’20)

Part 5: Join Algorithms

Oct 27 — Massively Parallel Sort-Merge Joins in Main Memory Multi-Core Database Systems (VLDB ’12)
Oct 29 — To Partition, or Not to Partition, That is the Join Question in a Real System (SIGMOD ’21)
Nov 3 — Robust Join Processing with Diamond Hardened Joins (VLDB ’24)
Nov 5 — Can Learned Models Replace Hash Functions? (VLDB ’22)
Nov 10 — Debunking the Myth of Join Ordering: Toward Robust SQL Analytics (SIGMOD ’25)

Part 6: Query Optimization

Nov 12 — How Good Are Query Optimizers, Really? (VLDB ’15)
Nov 17 — Learned Cardinalities: Estimating Correlated Joins with Deep Learning (CIDR ’19)
Nov 19 — Balsa: Learning a Query Optimizer Without Expert Demonstrations (SIGMOD ’22)
- Neo: A Learned Query Optimizer (VLDB ’19), optional
Nov 24 — Bao: Making Learned Query Optimization Practical (SIGMOD ’21)
- Deploying a Steered Query Optimizer in Production at Microsoft (SIGMOD ’22)
Dec 1 — Low Rank Learning for Offline Query Optimization (SIGMOD ’25)
Dec 3 — Adaptive and Robust Query Execution for Lakehouses at Scale (VLDB ’24)
Dec 8 — The Holon Approach for Simultaneously Tuning Multiple Components in a Self-Driving DBMS (VLDB ’24)