按年被提到
20222022 · 1 次2026
数学、逻辑与理论›AI 数学与定理证明·arXiv:2205.11491 · cs.CL

HyperTree Proof Search for Neural Theorem Proving

Guillaume Lample, Marie-Anne Lachaux, Thibaut Lavril, Xavier Martinet, Amaury Hayat, Gabriel Ebner, Aurélien Rodriguez, Timothée Lacroix · 2022
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2022-11-03 · 最近 2023-10-27
2不同的人
2活跃月份
2讨论串
53被引(OpenAlex)
arXiv 摘要(候选层不写导读)

We propose an online training procedure for a transformer-based automated theorem prover. Our approach leverages a new search algorithm, HyperTree Proof Search (HTPS), inspired by the recent success of AlphaZero. Our model learns from previous proof searches through online training, allowing it to generalize to domains far from the training distribution. We report detailed ablations of our pipeline's main components by studying performance on three environments of increasing complexity. In particular, we show that with HTPS alone, a model trained on annotated proofs manages to prove 65.4% of a held-out set of Metamath theorems, significantly outperforming the previous state of the art of 56.5% by GPT-f. Online training on these unproved theorems increases accuracy to 82.6%. With a similar computational budget, we improve the state of the art on the Lean-based miniF2F-curriculum dataset from 31% to 42% proving accuracy.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论aSanchezStern · 2023-10

“Sounds like you've stumbled into the wonderful world of machine-learning guided proof synthesis! While I don't think the full system you're describing has been built yet, many similar systems and pieces have. In terms of the initial phase of supervised learning on existing proofs to prove new ones, there's TacticToe (https://arxiv.org/abs/1804.00596), Tac…”

Lean4 helped Terence Tao discover a small bug in his recent paper原评论 ↗
被提交为 story · 1 次