About
People
Publications
Open Source
Demos
Events
Blog
Careers
Contact
English
English
Français
ServiceNow
ServiceNow Research
Tags
Generalization Guarranties
ServiceNow Research
Generalization Guarranties
Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks
Both PAC-Bayesian and Sample Compress learning frameworks have been shown instrumental for deriving tight (non-vacuous) generalization …
Benjamin Leblanc
,
Mathieu Bazinet
,
Nathaniel D'Amours
,
Alexandre Drouin
,
Pascal Germain
International Conference on Machine Learning (ICML), 2025.
PDF
Cite
Sample compression unleashed: New generalization bounds for real valued losses
The sample compression theory provides generalization guarantees for predictors that can be fully defined using a subset of the …
Mathieu Bazinet
,
Valentina Zantedeschi
,
Pascal Germain
International Conference on Artificial Intelligence and Statistics (AISTATS), 2025.
PDF
Cite
Sample Compression Hypernetworks: From Generalization Bounds to Meta-Learning
Reconstruction functions are pivotal in sample compression theory, a framework for deriving tight generalization bounds. From a small …
Benjamin Leblanc
,
Mathieu Bazinet
,
Nathaniel D'Amours
,
Pascal Germain
,
Alexandre Drouin
Workshop at the Neural Information Processing Systems (NeurIPS), 2024.
PDF
Cite
Sample compression unleashed: New generalization bounds for real valued losses
The sample compression theory provides generalization guarantees for predictors that can be fully defined using a subset of the …
Mathieu Bazinet
,
Valentina Zantedeschi
,
Pascal Germain
Workshop at the Neural Information Processing Systems (NeurIPS), 2024.
PDF
Cite
Generalization bounds with arbitrary complexity measures
In statistical learning theory, a generalization bound usually involves a complexity measure imposed by the considered theoretical …
Paul Viallard
,
Remi Emonet
,
Emilie Morvant
,
Amaury Habrard
,
Valentina Zantedeschi
International Conference on Artificial Intelligence and Statistics (AISTATS), 2024.
PDF
Cite
Egocentric Planning for Scalable Embodied Task Achievement
Embodied agents face significant challenges when tasked with performing actions in diverse environments, particularly in generalizing …
Xiaotian Liu
,
Hector Palacios
,
Christian Muise
Conference on Neural Information Processing Systems (NeurIPS), 2023.
PDF
Cite
On Margins and Generalisation for Voting Classifiers
We study the generalisation properties of majority voting on finite ensembles of classifiers, proving margin-based generalisation …
Felix Biggs
,
Valentina Zantedeschi
,
Benjamin Guedj
Conference on Neural Information Processing Systems (NeurIPS), 2022.
PDF
Cite
Code
A Planning based Neural-Symbolic Approach for Embodied Instruction Following
The ALFRED environment features an embodied agent following instructions and accomplishing tasks in simulated home environments. …
Xiaotian Liu
,
Hector Palacios
,
Christian Muise
Montreal AI Symposium (MAIS), 2022.
PDF
Cite
Scaling up ML-based Black-box Planning with Partial STRIPS Models
A popular approach for sequential decision-making is to perform simulator-based search guided with Machine Learning (ML) methods like …
Matias Greco
,
Alvaro Torralba
,
Jorge Baier
,
Hector Palacios
Workshop at International Join Conference on Artificial Intelligence (IJCAI), 2022.
PDF
Cite
Code
Scaling up ML-based Black-box Planning with Partial STRIPS Models
A popular approach for sequential decision-making is to perform simulator-based search guided with Machine Learning (ML) methods like …
Matias Greco
,
Alvaro Torralba
,
Jorge Baier
,
Hector Palacios
ICAPS'22 Workshop on Reliable Data-Driven Planning and Scheduling, 2022.
PDF
Cite
Code
»
Cite
×