Sign in to create and edit playbooks. Sign In Register

Randomly sample supertypes during training

randomly-sample-supertypes-during-training · always_apply: yes

Content

During training, randomly select a non-empty subset of τ(v) (the full supertype set) for each variable. This acts as dropout over the type lattice and ensures all known types in the lattice are trained. Use the full τ(v) at inference time.

Details
Slug:
randomly-sample-supertypes-during-training
Always apply:
Yes
Created:
May 20, 2026
Updated:
May 20, 2026
Playbook
Program Graphs for Code Analysis

v4.9

View Playbook
Activities 0

No activities linked.