Learning Certifiably Optimal Rule Lists: A Case for Discrete Optimization in the 21st Century

By Nicholas Larus-Stone. 2017

4 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Cynthia Rudin
2. Elaine Angelino
3. Jimmy J. Lin
4. Chudi Zhong
5. Margo I. Seltzer
6. Nicholas Larus-Stone
7. Daniel Alabi
8. Diane Hu

Citations in the corpus

• Generalized and Scalable Optimal Sparse Decision Trees (2020, methodology): “The CORELS algorithm (Angelino et al., 2017; 2018; Larus-Stone, 2017), which is an associative classification method rather than an optimal decision tree method, breaks away from the previous literature in that it is a custom branch-and-bound method with custom bounding theorems, its own bit-vector…”
• Systems Optimizations for Learning Certifiably Optimal Rule Lists (2018, methodology): “We experimented with multiple key types that could represent permutations of rule lists and found that a series of simple optimizations of the key and value types led to a 3x reduction in memory usage for the map [8].”