Theoretical Understanding of Classic Learning Algorithms

Información del proyecto

TUCLA

Identificador del acuerdo de subvención: 101125203

DOI

10.3030/101125203

Fecha de la firma de la CE 15 Diciembre 2023

Fecha de inicio 1 Agosto 2024

Fecha de finalización 31 Julio 2029

Financiado con arreglo a

• European Research Council (ERC)

Coste total

€ 1 999 288,00

Aportación de la UE

€ 1 999 288,00

Coordinado por

AARHUS UNIVERSITET
Denmark

CORDIS proporciona enlaces a los documentos públicos y las publicaciones de los proyectos de los programas marco HORIZONTE.

Los enlaces a los documentos y las publicaciones de los proyectos del Séptimo Programa Marco, así como los enlaces a algunos tipos de resultados específicos, como conjuntos de datos y «software», se obtienen dinámicamente de OpenAIRE .

Publicaciones

Conference proceedings (20)

Derandomizing Multi-Distribution Learning

Autores: Kasper Green Larsen, Omar Montasser, Nikita Zhivotovskiy
Publicado en: Advances in Neural Information Processing Systems 37, 2024
Editor: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.52202/079017-2989

Tight Margin-Based Generalization Bounds for Voting Classifiers over Finite Hypothesis Sets

Autores: Kasper Green Larsen, Natascha Schalburg
Publicado en: ICML 2026, 2026
Editor: PMLR
DOI: 10.48550/ARXIV.2511.20407

Revisiting Agnostic Boosting

Autores: Arthur da Cunha, Mikael Møller Høgsgaard, Andrea Paudice, Yuxin Sun
Publicado en: Advances in Neural Information Processing Systems 38, 2026
Editor: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.52202/085713-4698

Optimal Parallelization of Boosting

Autores: Arthur Da Cunha, Mikael Møller Høgsgaard, Kasper Green Larsen
Publicado en: Advances in Neural Information Processing Systems 37, 2024
Editor: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.52202/079017-0464

Learning with Monotone Adversarial Corruptions

Autores: Kasper Green Larsen, Chirag Pabbaraju, Abhishek Shetty
Publicado en: 2026
Editor: PMLR

Actively Learning Halfspaces without Synthetic Data

Autores: Hadley Black, Kasper Green Larsen, Arya Mazumdar, Barna Saha, Geelon So
Publicado en: 2026
Editor: PMLR

A New Lower Bound for Multicolor Discrepancy with Applications to Fair Division

Autores: Ioannis Caragiannis, Kasper Green Larsen, Sudarshan Shyam
Publicado en: Lecture Notes in Computer Science, Algorithmic Game Theory, 2025
Editor: Springer Nature Switzerland
DOI: 10.1007/978-3-032-03639-1_13

An Exponential Separation Between Quantum and Quantum-Inspired Classical Algorithms for Linear Systems

Autores: Allan Grønlund, Kasper Green Larsen
Publicado en: ICML 2026, 2026
Editor: PMLR
DOI: 10.48550/ARXIV.2411.02087

The Sample Complexity of Replicable Realizable PAC Learning

Autores: Kasper Green Larsen, Markus Engelund Mathiasen, Chirag Pabbaraju, Clement Svendsen
Publicado en: Proceedings of the 58th Annual ACM Symposium on Theory of Computing, 2026
Editor: ACM
DOI: 10.1145/3798129.3800910

Boosting, Voting Classifiers and Randomized Sample Compression Schemes

Autores: Arthur da Cunha, Kasper Green Larsen, Martin Ritzert
Publicado en: 2025
Editor: PMLR

On Agnostic PAC Learning in the Small Error Regime

Autores: Julian Asilis, Mikael Møller Høgsgaard, Grigoris Velegkas
Publicado en: Advances in Neural Information Processing Systems 38, 2026
Editor: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.52202/085713-4112

A Fine-Grained Understanding of Uniform Convergence for Halfspaces

Autores: Aryeh Kontorovich, Kasper Green Larsen
Publicado en: ICML 2026, 2026
Editor: PMLR
DOI: 10.48550/ARXIV.2605.06004

Revisiting Agnostic PAC Learning

Autores: Steve Hanneke, Kasper Green Larsen, Nikita Zhivotovskiy
Publicado en: 2024 IEEE 65th Annual Symposium on Foundations of Computer Science (FOCS), 2024
Editor: IEEE
DOI: 10.1109/FOCS61266.2024.00118

Improved Margin Generalization Bounds for Voting Classifiers

Autores: Mikael Møller Høgsgaard, Kasper Green Larsen
Publicado en: Proceedings of Thirty Eighth Conference on Learning Theory (series: Proceedings of Machine Learning Research), 2025
Editor: PMLR

The Interplay Between Interpolation and Aggregation in Regression: Optimal Sample Complexity

Autores: Mikael Møller Høgsgaard, Kasper Green Larsen, Liang-Yu Zou
Publicado en: ICML 2026, 2026
Editor: PMLR
DOI: 10.48550/ARXIV.2605.29819

The Optimal Sample Complexity of Linear Contracts

Autores: Mikael Møller Høgsgaard
Publicado en: ICML 2026, 2026
Editor: PMLR
DOI: 10.48550/ARXIV.2601.01496

The Many Faces of Optimal Weak-to-Strong Learning

Autores: Mikael Møller Høgsgaard, Kasper Green Larsen, Markus Engelund Mathiasen
Publicado en: Advances in Neural Information Processing Systems 37, 2024
Editor: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.52202/079017-1644

Sample-Near-Optimal Agnostic Boosting with Improved Running Time

Autores: Arthur da Cunha, Mikael Møller Høgsgaard, Andrea Paudice
Publicado en: Proceedings of The 37th International Conference on Algorithmic Learning Theory, 2026
Editor: PMLR

Improved Replicable Boosting with Majority-of-Majorities

Autores: Kasper Green Larsen, Markus Engelund Mathiasen, Clement Svendsen
Publicado en: 2026
Editor: PMLR

Tight Generalization Bounds for Large-Margin Halfspaces

Autores: Kasper Green Larsen, Natascha Schalburg
Publicado en: Advances in Neural Information Processing Systems 38, 2026
Editor: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.52202/085713-1531

Peer reviewed articles (1)

Fourth-moment theorems for sums of multiple integrals

Autores: Andreas Basse-O’Connor, David Kramer-Bang, Clement Svendsen
Publicado en: Proceedings of the American Mathematical Society, Edición 154, 2026, ISSN 1088-6826
Editor: American Mathematical Society (AMS)
DOI: 10.1090/PROC/17808