snrv.Snrv.fit

Snrv.fit(data, lag, ln_pathweight=None)[source]

fit SNRV model to data

Parameters

  • data (torch.tensor, n x dim, n = observations, dim = dimensionality of trajectory featurization) – trajectory

  • lag (int) – lag in steps to apply to data trajectory

  • ln_pathweight (torch.tensor, n, n = observations, default = None) – accumulated sum of the log Girsanov path weights between frames in the trajectory; Girsanov theorem measure of the probability of the observed sample path under a target potential relative to that which was actually observed under the simulation potential; identically unity (no reweighting rqd) for target potential == simulation potential and code as None; Ref.: Kieninger and Keller J. Chem. Phys 154 094102 (2021) https://doi.org/10.1063/5.0038408

Returns

  • self.lag (int) – lag in steps

  • self.training_losses (list, n_epoch) – loss over training data in each epoch

  • self.validation_losses (list, n_epoch) – loss over validation data in each epoch

  • self.evals (torch.tensor, n_comp, n_comp = no. of basis functions in ANN == output_size) – eigenvalues of VAC generalized eigenvalue problem finding linear combination of learned basis functions to produce approximations of transfer operator eigenvectors in non-ascending order OR singular values of VAMP singular value problem finding linear combination of learned basis functions to produce approximations of transfer operator left and right singular vectors in non-ascending order

  • self.expansion_coefficients (n_comp, n_comp = no. of basis functions in ANN == output_size) – expansion coefficients for linear combination of learned basis functions into transfer operator eigenvectors (reversible) or left singular vectors (non-reversible)

  • self.expansion_coefficients_right (n_comp, n_comp = no. of basis functions in ANN == output_size) – expansion coefficients for linear combination of learned basis functions into transfer operator right singular vectors (non-reversible)

  • self.is_fitted (bool) – indicator flag as to whether or nor model has been fitted