lean-proof-recording-public-old
Recording of tactic proofs in Lean 3 for machine learning
view repo
Labeled data for imitation learning of theorem proving in large libraries of formalized mathematics is scarce as such libraries require years of concentrated effort by human specialists to be built. This is particularly challenging when applying large Transformer language models to tactic prediction, because the scaling of performance with respect to model size is quickly disrupted in the data-scarce, easily-overfitted regime. We propose PACT (Proof Artifact Co-Training), a general methodology for extracting abundant self-supervised data from kernel-level proof terms for co-training alongside the usual tactic prediction objective. We apply this methodology to Lean, an interactive proof assistant which hosts some of the most sophisticated formalized mathematics to date. We instrument Lean with a neural theorem prover driven by a Transformer language model and show that PACT improves theorem proving success rate on a held-out suite of test theorems from 32% to 48%.
READ FULL TEXT
We explore the application of transformer-based language models to autom...
read it
We present miniF2F, a dataset of formal Olympiad-level mathematics probl...
read it
Mechanized theorem proving is becoming the basis of reliable systems
pro...
read it
Using an interactive theorem prover to reason about programs involves a
...
read it
We study the effectiveness of neural sequence models for premise selecti...
read it
Noisy data, non-convex objectives, model misspecification, and numerical...
read it
Neural models combining representation learning and reasoning in an
end-...
read it
Comments
There are no comments yet.