Zobrazeno 1 - 10
of 284
pro vyhledávání: '"Ek, Carl"'
Motivated by recent progress in the problem of numerical K\"ahler metrics, we survey machine learning techniques in this area, discussing both advantages and drawbacks. We then revisit the algebraic ansatz pioneered by Donaldson. Inspired by his work
Externí odkaz:
http://arxiv.org/abs/2410.11284
Learning complex robot behavior through interactions with the environment necessitates principled exploration. Effective strategies should prioritize exploring regions of the state-action space that maximize rewards, with optimistic exploration emerg
Externí odkaz:
http://arxiv.org/abs/2410.04988
Score-based models, trained with denoising score matching, are remarkably effective in generating high dimensional data. However, the high variance of their training objective hinders optimisation. We attempt to reduce it with a control variate, deri
Externí odkaz:
http://arxiv.org/abs/2408.12270
Sampling from generative models has become a crucial tool for applications like data synthesis and augmentation. Diffusion, Flow Matching and Continuous Normalizing Flows have shown effectiveness across various modalities, and rely on Gaussian latent
Externí odkaz:
http://arxiv.org/abs/2408.08558
Autor:
Roy, Hrittik, Miani, Marco, Ek, Carl Henrik, Hennig, Philipp, Pförtner, Marvin, Tatzel, Lukas, Hauberg, Søren
Current approximate posteriors in Bayesian neural networks (BNNs) exhibit a crucial limitation: they fail to maintain invariance under reparameterization, i.e. BNNs assign different posterior densities to different parametrizations of identical funct
Externí odkaz:
http://arxiv.org/abs/2406.03334
Riemannian geometry provides us with powerful tools to explore the latent space of generative models while preserving the underlying structure of the data. The latent space can be equipped it with a Riemannian metric, pulled back from the data manifo
Externí odkaz:
http://arxiv.org/abs/2212.10010
Adaptation-relevant predictions of climate change are often derived by combining climate model simulations in a multi-model ensemble. Model evaluation methods used in performance-based ensemble weighting schemes have limitations in the context of hig
Externí odkaz:
http://arxiv.org/abs/2211.16367
Autor:
Mikheeva, Olga, Kazlauskaite, Ieva, Hartshorne, Adam, Kjellström, Hedvig, Ek, Carl Henrik, Campbell, Neill D. F.
Multi-task learning requires accurate identification of the correlations between tasks. In real-world time-series, tasks are rarely perfectly temporally aligned; traditional multi-task models do not account for this and subsequent errors in correlati
Externí odkaz:
http://arxiv.org/abs/2110.15761
Autor:
Dutordoir, Vincent, Hensman, James, van der Wilk, Mark, Ek, Carl Henrik, Ghahramani, Zoubin, Durrande, Nicolas
Neural networks and Gaussian processes are complementary in their strengths and weaknesses. Having a better understanding of their relationship comes with the promise to make each method benefit from the strengths of the other. In this work, we estab
Externí odkaz:
http://arxiv.org/abs/2105.04504
Publikováno v:
In Advanced Engineering Informatics January 2024 59