Andreas Kipf

The Case for Synthesized Data Compression

Compression is a fundamental tool in data management. Today's compression schemes are generally designed by hand to apply to many different types of data (e.g., run length encoding or arithmetic encoding), leading to a zoo of general-purpose algorithms which work well for many datasets, but may not be optimal for any s...

High-Throughput LLM-Based Compression and What It Takes A Systems Study of Inference Engines and Entropy Coding Optimizations

MLSkip: Data Skipping for ML Filters via Lightweight Metadata

This work makes the case that Parquet's default min-max metadata is enough to enable pruning, and proposes an enhanced metadata structure: a size-bounded 2D convex hull that verification tools can make better use of, increasing the pruning effectiveness to 38.31%, while occupying at most 45 bytes per row group and colu...

Accelerating String-Heavy Queries with LLM Token Tables

Strings are the most common data type in modern database systems, yet they are often treated as an afterthought in high-performance data formats. While numerical data benefits from specialized, lightweight compression schemes, text is typically handled by general-purpose algorithms such as Zstd, LZ4, or Snappy, which r...

Improving Data Preparation for CSV Files with LLMs

This work shows how machine learning and GenAI can be used to assist with two specific tasks: First, when reading CSV files, it needs to be decided whether the first row is a header or not, and how machine learning and GenAI can be used to assist with two specific tasks.

Hollywood: Towards a Large Movie Dataset for Database Benchmarking

Hollywood is introduced, a synthetic IMDb-compatible benchmark generator that combines LLM-generated semantic dictionaries with deterministic temporal-graph-based relational data generation and demonstrates that Hollywood induces cardinality estimation errors comparable to or exceeding those observed on the original IM...