How Much Data Is Sufficient to Learn High-Performing Algorithms?: How much data is sufficient to learn high-performing algorithms?

Συγγραφείς: Maria-Florina Balcan, Dan Deblasio, Travis Dick, Carl Kingsford, Tuomas Sandholm, Ellen Vitercik

Πηγή: Journal of the ACM. 71:1-58

Θεματικοί όροι: 0301 basic medicine, data-driven algorithm design, 0303 health sciences, 03 medical and health sciences, machine learning, computational biology, General topics in the theory of algorithms, Learning and adaptive systems in artificial intelligence, automated algorithm design, automated algorithm configuration

Περιγραφή αρχείου: application/xml

Smoothed Analysis with Adaptive Adversaries

Συγγραφείς: Haghtalab, Nika, Roughgarden, Tim, Shetty, Abhishek

Πηγή: Journal of the ACM. 71(3):1-34

Διαθεσιμότητα: http://dl.acm.org/doi/10.1145/3656638

Data-Driven Solution Portfolios

Συγγραφείς: Drygala, Marina, Lattanzi, Silvio, Maggiori, Andreas, Stouras, Miltiadis, Svensson, Ola, Vassilvitskii, Sergei

Συνεισφορές: Marina Drygala and Silvio Lattanzi and Andreas Maggiori and Miltiadis Stouras and Ola Svensson and Sergei Vassilvitskii

Θεματικοί όροι: FOS: Computer and information sciences, data-driven algorithm design, Computer Science - Data Structures and Algorithms, solution portfolios, Data Structures and Algorithms (cs.DS), ddc:004, matroids

Περιγραφή αρχείου: application/pdf

Σύνδεσμος πρόσβασης: http://arxiv.org/abs/2412.00717
https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ITCS.2025.46

How much data is sufficient to learn high-performing algorithms? generalization guarantees for data-driven algorithm design

Συγγραφείς: Balcan, Maria-Florina, DeBlasio, Dan, Dick, Travis, Kingsford, Carl, Sandholm, Tuomas, Vitercik, Ellen

Πηγή: Proceedings of the 53rd Annual ACM SIGACT Symposium on Theory of Computing. :919-932

Διαθεσιμότητα: http://dl.acm.org/doi/10.1145/3406325.3451036

Data-Driven Solution Portfolios

Συγγραφείς: Drygala, Marina, Lattanzi, Silvio, Maggiori, Andreas, Stouras, Miltiadis, Svensson, Ola, Vassilvitskii, Sergei

Θεματικοί όροι: data-driven algorithm design, matroids, solution portfolios

Relation: 16th Innovations in Theoretical Computer Science Conference (ITCS 2025); Leibniz International Proceedings in Informatics (LIPIcs); 325; The 16th Annual Innovations in Theoretical Computer Science (ITCS) conference; #PLACEHOLDER_PARENT_METADATA_VALUE#; MB22.00054; https://infoscience.epfl.ch/handle/20.500.14299/247349

Διαθεσιμότητα: https://doi.org/10.4230/LIPIcs.ITCS.2025.46
https://infoscience.epfl.ch/handle/20.500.14299/247349
https://hdl.handle.net/20.500.14299/247349

Improved Sample Complexity Bounds for Branch-And-Cut

Συγγραφείς: Balcan, Maria-Florina, Prasad, Siddharth, Sandholm, Tuomas, Vitercik, Ellen

Συνεισφορές: Maria-Florina Balcan and Siddharth Prasad and Tuomas Sandholm and Ellen Vitercik

Θεματικοί όροι: Automated algorithm configuration, integer programming, machine learning theory, tree search, branch-and-bound, branch-and-cut, cutting planes, sample complexity, generalization guarantees, data-driven algorithm design

Περιγραφή αρχείου: application/pdf

Relation: Is Part Of LIPIcs, Volume 235, 28th International Conference on Principles and Practice of Constraint Programming (CP 2022); https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.CP.2022.3

Διαθεσιμότητα: https://doi.org/10.4230/LIPIcs.CP.2022.3
https://nbn-resolving.org/urn:nbn:de:0030-drops-166321
https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.CP.2022.3

Improved Sample Complexity Bounds for Branch-and-Cut

Συγγραφείς: Balcan, Maria-Florina, Prasad, Siddharth, Sandholm, Tuomas, Vitercik, Ellen

Συνεισφορές: Maria-Florina Balcan and Siddharth Prasad and Tuomas Sandholm and Ellen Vitercik

Θεματικοί όροι: FOS: Computer and information sciences, sample complexity, data-driven algorithm design, Computer Science - Machine Learning, tree search, Automated algorithm configuration, machine learning theory, Computer Science - Artificial Intelligence, 0211 other engineering and technologies, 02 engineering and technology, cutting planes, Machine Learning (cs.LG), branch-and-cut, Artificial Intelligence (cs.AI), generalization guarantees, Optimization and Control (math.OC), Computer Science - Data Structures and Algorithms, 0202 electrical engineering, electronic engineering, information engineering, FOS: Mathematics, branch-and-bound, Data Structures and Algorithms (cs.DS), ddc:004, integer programming, Mathematics - Optimization and Control

Περιγραφή αρχείου: application/pdf

Σύνδεσμος πρόσβασης: http://arxiv.org/abs/2111.11207
https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.CP.2022.3

Learning-based search algorithm design

Συγγραφείς: Chen, Binghong

Συνεισφορές: Zhang, Chao, Song, Le, Zhang, Xiuwei, Luo, Yunan, Fung, Victor, Computational Science and Engineering

Θεματικοί όροι: Learning to search, Data-driven algorithm design, Deep learning, Reinforcement learning, Meta-learning, Graph representation learning, Structured prediction, Robotics applications, AI for drug discovery, Chemistry applications

Περιγραφή αρχείου: application/pdf

Relation: https://hdl.handle.net/1853/72742

Διαθεσιμότητα: https://hdl.handle.net/1853/72742

Automated Algorithm and Mechanism Configuration

Συγγραφείς: Ellen Vitercik

Θεματικοί όροι: Applied computing not elsewhere classified, automated algorithm design, data-driven algorithm design, automated algorithm configuration, sample complexity, machine learning theory, mechanism design, Applied Computer Science

Relation: https://figshare.com/articles/thesis/Automated_Algorithm_and_Mechanism_Configuration/17207516

Διαθεσιμότητα: https://doi.org/10.1184/r1/17207516.v1
https://figshare.com/articles/thesis/Automated_Algorithm_and_Mechanism_Configuration/17207516

Learn to optimize-a brief overview.

Συγγραφείς: Tang K; Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, China., Yao X; Department of Computing and Decision Sciences, Lingnan University, Hong Kong 999077, China.

Πηγή: National science review [Natl Sci Rev] 2024 Apr 02; Vol. 11 (8), pp. nwae132. Date of Electronic Publication: 2024 Apr 02 (Print Publication: 2024).

Τύπος έκδοσης: Journal Article; Review

Στοιχεία περιοδικού: Publisher: China Science Publishing Country of Publication: China NLM ID: 101633095 Publication Model: eCollection Cited Medium: Internet ISSN: 2053-714X (Electronic) Linking ISSN: 2053714X NLM ISO Abbreviation: Natl Sci Rev Subsets: PubMed not MEDLINE

Improved Sample Complexity Bounds for Branch-And-Cut

Συγγραφείς: Maria-Florina Balcan and Siddharth Prasad and Tuomas Sandholm and Ellen Vitercik, Balcan, Maria-Florina, Prasad, Siddharth, Sandholm, Tuomas, Vitercik, Ellen

Όροι ευρετηρίου: Automated algorithm configuration, integer programming, machine learning theory, tree search, branch-and-bound, branch-and-cut, cutting planes, sample complexity, generalization guarantees, data-driven algorithm design, InProceedings, Text, doc-type:ResearchArticle, publishedVersion

Σύνδεσμος: https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.CP.2022.3
Is Part Of LIPIcs, Volume 235, 28th International Conference on Principles and Practice of Constraint Programming (CP 2022)