Database Paper Browser

Back to papers

Accelerating Machine Learning Inference with Probabilistic Predicates

Summary: Proposes probabilistic predicates to prune data blobs before expensive UDF feature extraction, with accuracy-aware filtering. Augments a cost-based optimizer to select plans from simple probabilistic predicates, enabling up to 10x ML inference speedups. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID
5471
Venue
SIGMOD
Year
2018
Pagerank
0.00027249545
Overall Rank
329 | 97.72%
DOI
10.1145/3183713.3183751

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 7 of 57 citing papers.

Previous Page 2 / 2 Next

Outgoing Citations (Sorted by Pagerank)

Showing 10 of 10 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Previous Page 1 / 1 Next

Semantically Similar Papers