Search Results for author:
Found 11 papers, 5 papers with code
Machine-Learned Premise Selection for Lean
For this purpose, we designed a custom version of the random forest model, trained in an online fashion.
MizAR 60 for Mizar 50
As a present to Mizar on its 50th anniversary, we develop an AI/TP system that automatically proves about 60\% of the Mizar theorems in the hammer setting.
Magnushammer: A Transformer-Based Approach to Premise Selection
By combining \method with a language-model-based automated theorem prover, we further improve the state-of-the-art proof success rate from $57. 0\%$ to $71. 0\%$ on the PISA benchmark using $4$x fewer parameters.
ProofNet: Autoformalizing and Formally Proving Undergraduate-Level Mathematics
We introduce ProofNet, a benchmark for autoformalization and formal proving of undergraduate-level mathematics.
Online Machine Learning Techniques for Coq: A Comparison
Learning happens in an online manner, meaning that Tactician's machine learning model is updated immediately every time the user performs a step in an interactive proof.
Stateful Premise Selection by Recurrent Neural Networks
In this work, we develop a new learning-based method for selecting facts (premises) when proving new goals over large formal libraries.
ENIGMA Anonymous: Symbol-Independent Inference Guiding Machine (system description)
For the neural guidance, we use symbol-independent graph neural networks (GNNs) and their embedding of the terms and clauses.
Can Neural Networks Learn Symbolic Rewriting?
This work investigates if the current neural architectures are adequate for learning symbolic rewriting.
Guiding Inferences in Connection Tableau by Recurrent Neural Networks
We present a dataset and experiments on applying recurrent neural networks (RNNs) for guiding clause selection in the connection tableau proof calculus.
ATPboost: Learning Premise Selection in Binary Setting with ATP Feedback
ATPboost is a system for solving sets of large-theory problems by interleaving ATP runs with state-of-the-art machine learning of premise selection from the proofs.
