Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Miller, Benjamin Kurt"'
Publikováno v:
NeurIPS 2024
Material discovery is a critical area of research with the potential to revolutionize various fields, including carbon capture, renewable energy, and electronics. However, the immense scale of the chemical space makes it challenging to explore all po
Externí odkaz:
http://arxiv.org/abs/2410.23405
Publikováno v:
ICML 2024
Crystalline materials are a fundamental component in next-generation technologies, yet modeling their distribution presents unique computational challenges. Of the plausible arrangements of atoms in a periodic lattice only a vanishingly small percent
Externí odkaz:
http://arxiv.org/abs/2406.04713
In Simulation-based Inference, the goal is to solve the inverse problem when the likelihood is only known implicitly. Neural Posterior Estimation commonly fits a normalized density estimator as a surrogate model for the posterior. This formulation ca
Externí odkaz:
http://arxiv.org/abs/2310.01808
Conservative inference is a major concern in simulation-based inference. It has been shown that commonly used algorithms can produce overconfident posterior approximations. Balancing has empirically proven to be an effective way to mitigate this issu
Externí odkaz:
http://arxiv.org/abs/2304.10978
The current and upcoming generations of gravitational wave experiments represent an exciting step forward in terms of detector sensitivity and performance. For example, key upgrades at the LIGO, Virgo and KAGRA facilities will see the next observing
Externí odkaz:
http://arxiv.org/abs/2304.02035
Likelihood-to-evidence ratio estimation is usually cast as either a binary (NRE-A) or a multiclass (NRE-B) classification task. In contrast to the binary classification framework, the current formulation of the multiclass version has an intrinsic and
Externí odkaz:
http://arxiv.org/abs/2210.06170
Autor:
Wang, Wujie, Xu, Minkai, Cai, Chen, Miller, Benjamin Kurt, Smidt, Tess, Wang, Yusu, Tang, Jian, Gómez-Bombarelli, Rafael
Publikováno v:
International Conference on Machine Learning (ICML), 2022
Coarse-graining (CG) of molecular simulations simplifies the particle representation by grouping selected atoms into pseudo-beads and drastically accelerates simulation. However, such CG procedure induces information losses, which makes accurate back
Externí odkaz:
http://arxiv.org/abs/2201.12176
Raw light curve data from exoplanet transits is too complex to naively apply traditional outlier detection methods. We propose an architecture which estimates a latent representation of both the main transit and residual deviations with a pair of var
Externí odkaz:
http://arxiv.org/abs/2111.08679
Autor:
Cole, Alex, Miller, Benjamin Kurt, Witte, Samuel J., Cai, Maxwell X., Grootes, Meiert W., Nattino, Francesco, Weniger, Christoph
Sampling-based inference techniques are central to modern cosmological data analysis; these methods, however, scale poorly with dimensionality and typically require approximate or intractable likelihoods. In this paper we describe how Truncated Margi
Externí odkaz:
http://arxiv.org/abs/2111.08030
Parametric stochastic simulators are ubiquitous in science, often featuring high-dimensional input parameters and/or an intractable likelihood. Performing Bayesian parameter inference in this context can be challenging. We present a neural simulation
Externí odkaz:
http://arxiv.org/abs/2107.01214