3.1k citations
- Centre National de la Recherche ScientifiqueFR63 papers
- Max Planck Institute for Radio AstronomyDE54 papers
- University of ManchesterGB50 papers
- Brookhaven National LaboratoryUS44 papers
- Netherlands Institute for Radio AstronomyNL43 papers
- Ruhr University BochumDE40 papers
- Université d'OrléansFR38 papers
- Université Paris CitéFR31 papers
- Commonwealth Scientific and Industrial Research OrganisationAU30 papers
- Laboratoire de Physique et Chimie de l’Environnement et de l’EspaceFR29 papers
- Universität HamburgDE27 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR26 papers
9 papers · 1 filter
Onsager's regression hypothesis adjusted to quantum systems
Peter Reimann, Christian Eidecker-Dunkel
Onsager's regression hypothesis connects the temporal relaxation of close-to-equilibrium systems with their dynamical correlation functions at thermal equilibrium. While the hypoth…
Intelligent Learning Rate Distribution to reduce Catastrophic Forgetting in Transformers
Philip Kenneweg, Alexander Schulz, Sarah Schröder +1
Pretraining language models on large text corpora is a common practice in natural language processing. Fine-tuning of these models is then performed to achieve the best results on…
Debiasing Sentence Embedders through Contrastive Word Pairs
Philip Kenneweg, Sarah Schröder, Alexander Schulz +1
Over the last years, various sentence embedders have been an integral part in the success of current machine learning approaches to Natural Language Processing (NLP). Unfortunately…
Neural Architecture Search for Sentence Classification with BERT
Philip Kenneweg, Sarah Schröder, Barbara Hammer
Pre training of language models on large text corpora is common practice in Natural Language Processing. Following, fine tuning of these models is performed to achieve the best res…
Faster Convergence for Transformer Fine-tuning with Line Search Methods
Philip Kenneweg, Leonardo Galli, Tristan Kenneweg +1
Recent works have shown that line search methods greatly increase performance of traditional stochastic gradient descent methods on a variety of datasets and architectures [1], [2]…
Average dissipation for stochastic transport equations with Lévy noise
Franco Flandoli, Andrea Papini, Marco Rehmeier
We show that, in one spatial and arbitrary jump dimension, the averaged solution of a Marcustype SPDE with pure jump Lévy transport noise satisfies a dissipative deterministic equa…