paper-with-me

Papers

First Neural Conjecturing Datasets and Experiments

2020-05-29 · Josef Urban, Jan Jakubův

We describe several datasets and first experiments with creating conjectures by neural methods. The datasets are based on the Mizar Mathematical Library processed in several forms and the problems extracted from it by the MPTP system and proved by the E prover using the ENIGMA guidance. The conjecturing experiments use the Transformer architecture and in particular its GPT-2 implementation.

📄 PDF Abstract BibTeX arXiv:2005.14664

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Weight Decay 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…
Discriminative Fine-Tuning Discriminative Fine-Tuning is a fine-tuning strategy that is used for ULMFiT type models. Instead of using the same learning rate…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Conjecturing: An Overlooked Step in Formal Mathematical Reasoning

2025-10-13 · Jasivan Alex Sivakumar, Philipp Borchert, Ronald Cardenas, Gerasimos Lampouras arxiv

Autoformalisation, the task of expressing informal mathematical statements in formal language, is often viewed as a direct translation process. This, however, disregards a critical preceding step: conjecturing. Many math…

Mathematical Reasoning

Lemmanaid: Neuro-Symbolic Lemma Conjecturing

2025-04-07 · Yousef Alhessi, Sólrún Halla Einarsdóttir, George Granberry, Emily First 외

Automatically conjecturing useful, interesting and novel lemmas would greatly improve automated reasoning tools and lower the bar for formalizing mathematics in proof assistants. It is however a very challenging task for…

LEMMA

Conjecturing-Based Discovery of Patterns in Data

2020-11-23 · J. P. Brooks, D. J. Edwards, C. E. Larson, N. Van Cleemput

We propose the use of a conjecturing machine that suggests feature relationships in the form of bounds involving nonlinear terms for numerical features and boolean expressions for categorical features. The proposed Conje…

BIG-bench Machine LearningregressionSymbolic Regression

Machine Learning meets Algebraic Combinatorics: A Suite of Datasets Capturing Research-level Conjecturing Ability in Pure Mathematics

2025-03-09 · Herman Chau, Helen Jenne, Davis Brown, Jesse He 외

With recent dramatic increases in AI system capabilities, there has been growing interest in utilizing machine learning for reasoning-heavy, quantitative tasks, particularly mathematics. While there are many resources ca…

Abstract AlgebraProgram Synthesis

Discovering New Theorems via LLMs with In-Context Proof Learning in Lean

2025-09-16 · Kazumi Kasaura, Naoto Onda, Yuta Oriike, Masaya Taniguchi 외 arxiv

Large Language Models (LLMs) have demonstrated significant promise in formal theorem proving. In this study, we investigate the ability of LLMs to discover novel theorems and produce verified proofs. We propose a pipelin…