Formal Mathematics Statement Curriculum Learning

02/03/2022
by   Stanislas Polu, et al.
0

We explore the use of expert iteration in the context of language modeling applied to formal mathematics. We show that at same compute budget, expert iteration, by which we mean proof search interleaved with learning, dramatically outperforms proof search only. We also observe that when applied to a collection of formal statements of sufficiently varied difficulty, expert iteration is capable of finding and solving a curriculum of increasingly difficult problems, without the need for associated ground-truth proofs. Finally, by applying this expert iteration to a manually curated set of problem statements, we achieve state-of-the-art on the miniF2F benchmark, automatically solving multiple challenging problems drawn from high school olympiads.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/31/2021

MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics

We present miniF2F, a dataset of formal Olympiad-level mathematics probl...
research
11/14/2022

Towards a Mathematics Formalisation Assistant using Large Language Models

Mathematics formalisation is the task of writing mathematics (i.e., defi...
research
02/24/2023

ProofNet: Autoformalizing and Formally Proving Undergraduate-Level Mathematics

We introduce ProofNet, a benchmark for autoformalization and formal prov...
research
11/29/2022

Peano: Learning Formal Mathematical Reasoning

General mathematical reasoning is computationally undecidable, but human...
research
12/05/2019

Exploration of Neural Machine Translation in Autoformalization of Mathematics in Mizar

In this paper we share several experiments trying to automatically trans...
research
05/10/2018

First Experiments with Neural Translation of Informal to Formal Mathematics

We report on our first experiments to train deep neural networks that au...
research
02/17/2022

Robust Reinforcement Learning via Genetic Curriculum

Achieving robust performance is crucial when applying deep reinforcement...

Please sign up or login with your details

Forgot password? Click here to reset