English
Related papers

Related papers: ENIGMAWatch: ProofWatch Meets ENIGMA

200 papers

This work describes a new version of a previously published Python package - gym-saturation: a collection of OpenAI Gym environments for guiding saturation-style provers based on the given clause algorithm with reinforcement learning. We…

Machine Learning · Computer Science 2023-09-19 Boris Shminke

Due to recent empirical successes, the options framework for hierarchical reinforcement learning is gaining increasing popularity. Rather than learning from rewards which suffers from the curse of dimensionality, we consider learning an…

Machine Learning · Computer Science 2021-02-16 Zhiyu Zhang , Ioannis Paschalidis

In this paper, a novel multimode dynamic process monitoring approach is proposed by extending elastic weight consolidation (EWC) to probabilistic slow feature analysis (PSFA) in order to extract multimode slow features for online…

Machine Learning · Computer Science 2022-04-29 Jingxin Zhang , Donghua Zhou , Maoyin Chen , Xia Hong

While theories postulating a dual cognitive system take hold, quantitative confirmations are still needed to understand and identify interactions between the two systems or conflict events. Eye movements are among the most direct markers of…

Neurons and Cognition · Quantitative Biology 2020-02-27 Alessandro Rossi , Sara Ermini , Dario Bernabini , Dario Zanca , Marino Todisco , Alessandro Genovese , Antonio Rizzo

Fast and accurate load parameters identification has great impact on the power systems operation and stability analysis. This paper proposes a novel transfer reinforcement learning based method to identify composite ZIP and induction motor…

Signal Processing · Electrical Eng. & Systems 2019-05-08 Jian Xie , Zixiao Ma , Zhaoyu Wang , Fankun Bu

Automated theorem proving has long been a key task of artificial intelligence. Proofs form the bedrock of rigorous scientific inquiry. Many tools for both partially and fully automating their derivations have been developed over the last…

Artificial Intelligence · Computer Science 2018-10-15 Brian Groenke

Modern instance-based model-agnostic explanation methods (LIME, SHAP, L2X) are of great use in data-heavy industries for model diagnostics, and for end-user explanations. These methods generally return either a weighting or subset of input…

Machine Learning · Computer Science 2019-12-03 Matt Chapman-Rounds , Marc-Andre Schulz , Erik Pazos , Konstantinos Georgatzis

Demonstration learning aims to guide the prompt prediction via providing answered demonstrations in the few shot settings. Despite achieving promising results, existing work only concatenates the answered examples as demonstrations to the…

Machine Learning · Computer Science 2022-09-02 Sirui Wang , Kaiwen Wei , Hongzhi Zhang , Yuntao Li , Wei Wu

Recent advancements in meta-learning have enabled the automatic discovery of novel reinforcement learning algorithms parameterized by surrogate objective functions. To improve upon manually designed algorithms, the parameterization of this…

This paper presents a novel approach for augmenting proof-based verification with performance-style analysis of the kind employed in state-of-the-art model checking tools for probabilistic systems. Quantitative safety properties usually…

Logic in Computer Science · Computer Science 2009-12-11 Ukachukwu Ndukwu

Imitation learning allows agents to learn complex behaviors from demonstrations. However, learning a complex vision-based task may require an impractical number of demonstrations. Meta-imitation learning is a promising approach towards…

Universal quantifiers occur frequently in proof obligations produced by program verifiers, for instance, to axiomatize uninterpreted functions and to express properties of arrays. SMT-based verifiers typically reason about them via…

Programming Languages · Computer Science 2021-12-15 Alexandra Bugariu , Arshavir Ter-Gabrielyan , Peter Müller

Reinforcement learning algorithms need exploration to learn. However, unsupervised exploration prevents the deployment of such algorithms on safety-critical tasks and limits real-world deployment. In this paper, we propose a new algorithm…

Machine Learning · Computer Science 2024-02-07 Sven Gronauer , Tom Haider , Felippe Schmoeller da Roza , Klaus Diepold

Hierarchical beam search in mmWave communications incurs substantial training overhead, necessitating deep learning-enabled beam predictions to effectively leverage channel priors and mitigate this overhead. In this study, we introduce a…

Information Theory · Computer Science 2024-01-04 Fan Meng , Cheng Zhang , Yongming Huang , Zhilei Zhang , Xiaoyu Bai , Zhaohua Lu

Iterative preference optimization methods have recently been shown to perform well for general instruction tuning tasks, but typically make little improvement on reasoning tasks (Yuan et al., 2024, Chen et al., 2024). In this work we…

Computation and Language · Computer Science 2024-06-27 Richard Yuanzhe Pang , Weizhe Yuan , Kyunghyun Cho , He He , Sainbayar Sukhbaatar , Jason Weston

We present automated theorem provers for the first-order logic of here and there (HT). They are based on a native sequent calculus for the logic of HT and an axiomatic embedding of the logic of HT into intuitionistic logic. The analytic…

Logic in Computer Science · Computer Science 2026-01-08 Jens Otten , Torsten Schaub

Solving mathematical reasoning problems requires not only accurate access to relevant knowledge but also careful, multi-step thinking. However, current retrieval-augmented models often rely on a single perspective, follow inflexible search…

Artificial Intelligence · Computer Science 2025-11-03 Ali Asgarov , Umid Suleymanov , Aadyant Khatri

Commonly used proof strategies by automated reasoners organise proof search either by ordering-based saturation or by reducing goals to subgoals. In this paper, we combine these two approaches and advocate a SAT-based method with symmetry…

Logic in Computer Science · Computer Science 2026-03-09 Clemens Eisenhofer , Michael Rawson , Laura Kovács

We introduce a proof recommender system for the HOL4 theorem prover. Our tool is built upon a transformer-based model [2] designed specifically to provide proof assistance in HOL4. The model is trained to discern theorem proving patterns…

Logic in Computer Science · Computer Science 2025-01-13 Nour Dekhil , Adnan Rashid , Sofiene Tahar

Prompting methods recently achieve impressive success in few-shot learning. These methods modify input samples with prompt sentence pieces, and decode label tokens to map samples to corresponding labels. However, such a paradigm is very…

Computation and Language · Computer Science 2022-04-05 Yutai Hou , Cheng Chen , Xianzhen Luo , Bohan Li , Wanxiang Che