Zobrazeno 1 - 10
of 7 373
pro vyhledávání: '"Lobato Á"'
Developing an efficient sampler capable of generating independent and identically distributed (IID) samples from a Boltzmann distribution is a crucial challenge in scientific research, e.g. molecular dynamics. In this work, we intend to learn neural
Externí odkaz:
http://arxiv.org/abs/2409.09787
Autor:
Zhang, Fengzhe, He, Jiajun, Midgley, Laurence I., Antorán, Javier, Hernández-Lobato, José Miguel
Diffusion models have shown promising potential for advancing Boltzmann Generators. However, two critical challenges persist: (1) inherent errors in samples due to model imperfections, and (2) the requirement of hundreds of functional evaluations (NF
Externí odkaz:
http://arxiv.org/abs/2409.07323
Autor:
Bergna, Richard, Calvo-Ordoñez, Sergio, Opolka, Felix L., Liò, Pietro, Hernandez-Lobato, Jose Miguel
We address the problem of learning uncertainty-aware representations for graph-structured data. While Graph Neural Ordinary Differential Equations (GNODE) are effective in learning node representations, they fail to quantify uncertainty. To address t
Externí odkaz:
http://arxiv.org/abs/2408.16115
Publikováno v:
Physica Scripta, Volume 99, Issue 6, id.065050, 2024
Among the recent extensions to standard General Relativity, $f(R,\mathcal{L}_m)$ gravity has risen an interest given the possibility of coupling between geometry and matter. We examine the simplest model with non-minimal coupling in the context of co
Externí odkaz:
http://arxiv.org/abs/2408.00580
Progress in neuroscience has provided unprecedented opportunities to advance our understanding of brain alterations and their correspondence to phenotypic profiles. With data collected from various imaging techniques, studies have integrated differen
Externí odkaz:
http://arxiv.org/abs/2407.21154
Wave propagation is a common occurrence in all of physics. A linear approximation provides a simpler way to describe various fields related to observable phenomena in laboratory physics as well as astronomy and cosmology, allowing us to probe gravita
Externí odkaz:
http://arxiv.org/abs/2407.04627
Bayesian optimization (BO) is a principled approach to molecular design tasks. In this paper we explain three pitfalls of BO which can cause poor empirical performance: an incorrect prior width, over-smoothing, and inadequate acquisition function max
Externí odkaz:
http://arxiv.org/abs/2406.07709
Autor:
Kulytė, Paulina, Vargas, Francisco, Mathis, Simon Valentin, Wang, Yu Guang, Hernández-Lobato, José Miguel, Liò, Pietro
Antibodies, crucial for immune defense, primarily rely on complementarity-determining regions (CDRs) to bind and neutralize antigens, such as viruses. The design of these CDRs determines the antibody's affinity and specificity towards its target. Gen
Externí odkaz:
http://arxiv.org/abs/2406.05832
Autor:
Lin, Jihao Andreas, Padhy, Shreyas, Mlodozeniec, Bruno, Antorán, Javier, Hernández-Lobato, José Miguel
Scaling hyperparameter optimisation to very large datasets remains an open problem in the Gaussian process community. This paper focuses on iterative methods, which use linear system solvers, like conjugate gradients, alternating projections or stoch
Externí odkaz:
http://arxiv.org/abs/2405.18457
Gaussian processes are a versatile probabilistic machine learning model whose effectiveness often depends on good hyperparameters, which are typically learned by maximising the marginal likelihood. In this work, we consider iterative methods, which u
Externí odkaz:
http://arxiv.org/abs/2405.18328