
Training a FirstOrder Theorem Prover from Synthetic Data
A major challenge in applying machine learning to automated theorem prov...
read it

Data Generation for Neural Programming by Example
Programming by example is the problem of synthesizing a program from a s...
read it

INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving
In learningassisted theorem proving, one of the most critical challenge...
read it

Automated Generation of Geometric Theorems from Images of Diagrams
We propose an approach to generate geometric theorems from electronic im...
read it

Learning to Prove Theorems via Interacting with Proof Assistants
Humans prove theorems by relying on substantial highlevel reasoning and...
read it

TacticZero: Learning to Prove Theorems from Scratch with Deep Reinforcement Learning
We propose a novel approach to interactive theoremproving (ITP) using d...
read it

Training Data Augmentation for Deep Learning RF Systems
Applications of machine learning are subject to three major components t...
read it
Learning to Prove from Synthetic Theorems
A major challenge in applying machine learning to automated theorem proving is the scarcity of training data, which is a key ingredient in training successful deep learning models. To tackle this problem, we propose an approach that relies on training with synthetic theorems, generated from a set of axioms. We show that such theorems can be used to train an automated prover and that the learned prover transfers successfully to humangenerated theorems. We demonstrate that a prover trained exclusively on synthetic theorems can solve a substantial fraction of problems in TPTP, a benchmark dataset that is used to compare stateoftheart heuristic provers. Our approach outperforms a model trained on humangenerated problems in most axiom sets, thereby showing the promise of using synthetic data for this task.
READ FULL TEXT
Comments
There are no comments yet.