Zobrazeno 1 - 10
of 67
pro vyhledávání: '"Kessel, Pan"'
Equivariant neural networks have in recent years become an important technique for guiding architecture selection for neural networks with many applications in domains ranging from medical image analysis to quantum chemistry. In particular, as the mo
Externí odkaz:
http://arxiv.org/abs/2406.06504
Autor:
Nicoli, Kim A., Anders, Christopher J., Funcke, Lena, Hartung, Tobias, Jansen, Karl, Kühn, Stefan, Müller, Klaus-Robert, Stornati, Paolo, Kessel, Pan, Nakajima, Shinichi
In this paper, we propose a novel and powerful method to harness Bayesian optimization for Variational Quantum Eigensolvers (VQEs) -- a hybrid quantum-classical protocol used to approximate the ground state of a quantum Hamiltonian. Specifically, we
Externí odkaz:
http://arxiv.org/abs/2406.06150
Recent work shows that path gradient estimators for normalizing flows have lower variance compared to standard estimators for variational inference, resulting in improved training. However, they are often prohibitively more expensive from a computati
Externí odkaz:
http://arxiv.org/abs/2403.15881
Autor:
Gerken, Jan E., Kessel, Pan
We show that deep ensembles become equivariant for all inputs and at all training times by simply using data augmentation. Crucially, equivariance holds off-manifold and for any architecture in the infinite width limit. The equivariance is emergent i
Externí odkaz:
http://arxiv.org/abs/2403.03103
In silico screening uses predictive models to select a batch of compounds with favorable properties from a library for experimental validation. Unlike conventional learning paradigms, success in this context is measured by the performance of the pred
Externí odkaz:
http://arxiv.org/abs/2307.09379
Autor:
Nicoli, Kim A., Anders, Christopher J., Hartung, Tobias, Jansen, Karl, Kessel, Pan, Nakajima, Shinichi
We study the consequences of mode-collapse of normalizing flows in the context of lattice field theory. Normalizing flows allow for independent sampling. For this reason, it is hoped that they can avoid the tunneling problem of local-update MCMC algo
Externí odkaz:
http://arxiv.org/abs/2302.14082
We propose a unifying approach that starts from the perturbative construction of trivializing maps by L\"uscher and then improves on it by learning. The resulting continuous normalizing flow model can be implemented using common tools of lattice fiel
Externí odkaz:
http://arxiv.org/abs/2212.08469
We propose an algorithm to estimate the path-gradient of both the reverse and forward Kullback-Leibler divergence for an arbitrary manifestly invertible normalizing flow. The resulting path-gradient estimators are straightforward to implement, have l
Externí odkaz:
http://arxiv.org/abs/2207.08219
Recent work has established a path-gradient estimator for simple variational Gaussian distributions and has argued that the path-gradient is particularly beneficial in the regime in which the variational distribution approaches the exact target distr
Externí odkaz:
http://arxiv.org/abs/2206.09016
Counterfactuals can explain classification decisions of neural networks in a human interpretable way. We propose a simple but effective method to generate such counterfactuals. More specifically, we perform a suitable diffeomorphic coordinate transfo
Externí odkaz:
http://arxiv.org/abs/2206.05075