Stochastic Normalizing Flows

Authors: Hao Wu, Jonas Köhler, Frank Noe

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We illustrate the representational power, sampling efficiency and asymptotic correctness of SNFs on several benchmarks including applications to sampling molecular systems in equilibrium. We apply the model to the recently introduced problem of asymptotically unbiased sampling of molecular structures with flows [32] and show that it significantly improves sampling the multi-modal torsion angle distributions which are the relevant degrees of freedom in the system. We further show the advantage of the method over pure flow-based sampling / MCMC by quantitative comparison on benchmark data sets and on sampling from a VAE s posterior distribution.
Researcher Affiliation Academia Hao Wu Tongji University Shanghai, P.R. China wwtian@gmail.com Jonas Köhler FU Berlin Berlin, Germany jonas.koehler@fu-berlin.de Frank Noé FU Berlin Berlin, Germany frank.noe@fu-berlin.de
Pseudocode No The paper describes the methods and equations but does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes Code is available at github.com/noegroup/stochastic_normalizing_flows
Open Datasets Yes Table 3 shows results for the variational bound and the log likelihood on the test set for MNIST [23] and Fashion-MNIST [44].
Dataset Splits No The paper mentions using "test set" for MNIST and Fashion-MNIST but does not provide specific details on the training, validation, and test splits, percentages, or sample counts, nor does it cite the specific split methodology used.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details, such as library or solver names with version numbers, needed to replicate the experiment.
Experiment Setup No The paper refers to supplementary materials for detailed experimental setup information (e.g., 'Details in Suppl. Material Sec. 9' and 'See Suppl. Material Sec. 8 for details.'), and specific hyperparameter values or training configurations are not explicitly provided in the main text.