In this session, Bob Carpenter will present the following paper:Hamiltonian Graph Networks with ODE Integrators
http://arxiv.org/abs/1909.12790
** GENERAL ANNOUNCEMENT
We are currently running a series on "Learning & sampling physical models”. A list of potential references is included below, suggestions of others are more than welcome. Anyone interested in presenting for the series, please email Marylou Gabrié.
** References:
https://arxiv.org/abs/1711.09268 - GENERALIZING HAMILTONIAN MONTE CARLO WITH NEURAL NETWORKS
http://arxiv.org/abs/1910.00753 Equivariant Flows: sampling configurations for multi-body systems with symmetric energies
http://arxiv.org/abs/1410.6460 Markov Chain Monte Carlo and variational inference: Bridging the gap
http://arxiv.org/abs/2002.04292 Boosting Monte Carlo simulations of spin glasses using autoregressive neural networks
http://arxiv.org/abs/2008.06334 Learning with rare data: Using active importance sampling to optimize objectives dominated by rare events
http://dx.doi.org/10.1038/s41567-020-0842-8%0Ahttp://www.nature.com/articles/s41567-020-0842-8Unveiling the predictive power of static structure in glassy systems