Machine-Learned Dynamical Representations for Accelerated RiteWeight Convergence

Abstract

The increasing use of generative models has made ensembles of short molecular dynamics trajectories increasingly common, creating a growing need for methods that can recover physically meaningful steady-state populations and kinetics from improperly weighted conformational ensembles. Randomized Iterative Trajectory Reweighting (RiteWeight) addresses this problem through repeated random clustering and iterative reweighting, without requiring the fixed Markovian discretization used in conventional Markov state models (MSM). However, the choice of reduced feature space in which RiteWeight performs random clustering has not been systematically investigated. Here, we compare two machine-learned representations, DeepTICA and SPIB-VAE, with linear TICA for recovering steady-state observables from flawed distributions. DeepTICA learns nonlinear coordinates by targeting slow transfer-operator eigenmodes, whereas SPIB-VAE compresses configurations into a low-dimensional latent space while retaining information predictive of future metastable states. DeepTICA provided a comparatively robust RiteWeight representation under limited hyperparameter exploration, whereas SPIB-VAE benefited more strongly from broader optimization. Moreover, a kinetic score computed from a coarse MSM at a resolution comparable to that used for RiteWeight random clustering provided a useful criterion for efficiently selecting reduced representations and their hyperparameters for RiteWeight.

SelfTICA: contrastive learning of dynamical representations for rare-event sampling and characterization
Kai Zhu, Jintu Zhang, Pietro Novelli +2
arXiv9 Sep 2026PreprintarXiv licenceFull textPhysical chemistry Computational physicsarXiv
Machine learning-accelerated evolutionary Monte Carlo for rapid phase exploration of compositionally complex materials in reactive environments
Shuang Han, Sandip De
ChemRxiv9 Sep 2026PreprintCC BYMaterials & polymersChemRxiv
Machine Learning-Accelerated Inverse Design of Sequence-Controlled Terpolymers
Jeffrey C. Foster
ChemRxiv4 Oct 2026PreprintCC BY-NCFull textMaterials & polymersChemRxiv
Electronic configuration vectors provide transferable elemental representations for machine learning across the periodic table
Raghavendra Rajagopalan, Ananth Govind Rajan
ChemRxiv3 Sep 2026PreprintCC BY-NC-NDFull textMaterials & polymersChemRxiv
Polymer Informatics Atlas: Property-Specific Representations, Chemistry-Aware Generalization, and Reliability-Aware Machine Learning Across Five Polymer Properties
Dennis Obinna Orji
ChemRxiv17 Sep 2026PreprintCC BYFull textMaterials & polymersChemRxiv

Cite

BibTeX RIS

BibTeX

@misc{kania2026machinelearned,
  title = {{Machine-Learned Dynamical Representations for Accelerated RiteWeight Convergence}},
  author = {Sagar Kania},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.19388},
  eprint = {2609.19388},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.19388},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - Machine-Learned Dynamical Representations for Accelerated RiteWeight Convergence
AU  - Sagar Kania
PY  - 2026
DA  - 2026/09/16
PB  - arXiv
DO  - 10.48550/arxiv.2609.19388
UR  - https://arxiv.org/abs/2609.19388
AB  - The increasing use of generative models has made ensembles of short molecular dynamics trajectories increasingly common, creating a growing need for methods that can recover physically meaningful steady-state populations and kinetics from improperly weighted conformational ensembles. Randomized Iterative Trajectory Reweighting (RiteWeight) addresses this problem through repeated random clustering and iterative reweighting, without requiring the fixed Markovian discretization used in conventional Markov state models (MSM). However, the choice of reduced feature space in which RiteWeight performs random clustering has not been systematically investigated. Here, we compare two machine-learned representations, DeepTICA and SPIB-VAE, with linear TICA for recovering steady-state observables from flawed distributions. DeepTICA learns nonlinear coordinates by targeting slow transfer-operator eigenmodes, whereas SPIB-VAE compresses configurations into a low-dimensional latent space while retaining information predictive of future metastable states. DeepTICA provided a comparatively robust RiteWeight representation under limited hyperparameter exploration, whereas SPIB-VAE benefited more strongly from broader optimization. Moreover, a kinetic score computed from a coarse MSM at a resolution comparable to that used for RiteWeight random clustering provided a useful criterion for efficiently selecting reduced representations and their hyperparameters for RiteWeight.
ER  -

Abstract

Related

Cite