Zobrazeno 1 - 10
of 268
pro vyhledávání: '"Filippone, Maurizio"'
Introducing training-time augmentations is a key technique to enhance generalization and prepare deep neural networks against test-time corruptions. Inspired by the success of generative diffusion models, we propose a novel approach coupling data aug
Externí odkaz:
http://arxiv.org/abs/2406.01494
A Multi-step Loss Function for Robust Learning of the Dynamics in Model-based Reinforcement Learning
In model-based reinforcement learning, most algorithms rely on simulating trajectories from one-step models of the dynamics learned on data. A critical challenge of this approach is the compounding of one-step prediction errors as the length of the t
Externí odkaz:
http://arxiv.org/abs/2402.03146
Autor:
Bonilla, Edwin V., Elinas, Pantelis, Zhao, He, Filippone, Maurizio, Kitsios, Vassili, O'Kane, Terry
Estimating the structure of a Bayesian network, in the form of a directed acyclic graph (DAG), from observational data is a statistically and computationally hard problem with essential applications in areas such as causal discovery. Bayesian approac
Externí odkaz:
http://arxiv.org/abs/2402.02644
Autor:
Papamarkou, Theodore, Skoularidou, Maria, Palla, Konstantina, Aitchison, Laurence, Arbel, Julyan, Dunson, David, Filippone, Maurizio, Fortuin, Vincent, Hennig, Philipp, Hernández-Lobato, José Miguel, Hubin, Aliaksandr, Immer, Alexander, Karaletsos, Theofanis, Khan, Mohammad Emtiyaz, Kristiadi, Agustinus, Li, Yingzhen, Mandt, Stephan, Nemeth, Christopher, Osborne, Michael A., Rudner, Tim G. J., Rügamer, David, Teh, Yee Whye, Welling, Max, Wilson, Andrew Gordon, Zhang, Ruqi
In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooke
Externí odkaz:
http://arxiv.org/abs/2402.00809
Autor:
Zammit-Mangion, Andrew, Kaminski, Michael D., Tran, Ba-Hien, Filippone, Maurizio, Cressie, Noel
interpretable, and well understood models that are routinely employed even though, as is revealed through prior and posterior predictive checks, these can poorly characterise the spatial heterogeneity in the underlying process of interest. Here, we p
Externí odkaz:
http://arxiv.org/abs/2311.09491
In model-based reinforcement learning (MBRL), most algorithms rely on simulating trajectories from one-step dynamics models learned on data. A critical challenge of this approach is the compounding of one-step prediction errors as length of the traje
Externí odkaz:
http://arxiv.org/abs/2310.05672
Generative Models (GMs) have attracted considerable attention due to their tremendous success in various domains, such as computer vision where they are capable to generate impressive realistic-looking images. Likelihood-based GMs are attractive due
Externí odkaz:
http://arxiv.org/abs/2305.18900
Autor:
Gogolashvili, Davit, Zecchin, Matteo, Kanagawa, Motonobu, Kountouris, Marios, Filippone, Maurizio
This paper investigates when the importance weighting (IW) correction is needed to address covariate shift, a common situation in supervised learning where the input distributions of training and test data differ. Classic results show that the IW cor
Externí odkaz:
http://arxiv.org/abs/2303.04020
Autor:
Franzese, Giulio, Corallo, Giulio, Rossi, Simone, Heinonen, Markus, Filippone, Maurizio, Michiardi, Pietro
We introduce Functional Diffusion Processes (FDPs), which generalize score-based diffusion models to infinite-dimensional function spaces. FDPs require a new mathematical framework to describe the forward and backward dynamics, and several extensions
Externí odkaz:
http://arxiv.org/abs/2303.00800
Autoencoders and their variants are among the most widely used models in representation learning and generative modeling. However, autoencoder-based models usually assume that the learned representations are i.i.d. and fail to capture the correlation
Externí odkaz:
http://arxiv.org/abs/2302.04534