From Biased to Unbiased Dynamics: An Infinitesimal Generator Approach

• URL: http://arxiv.org/abs/2406.09028v1
• Date: Thu, 13 Jun 2024 12:02:51 GMT
• Title: From Biased to Unbiased Dynamics: An Infinitesimal Generator Approach
• Authors: Timothée Devergne, Vladimir Kostic, Michele Parrinello, Massimiliano Pontil,
• Abstract summary: We investigate learning the eigenfunctions of evolution operators for time-reversal invariant processes. Many physical or chemical processes described by the Langevin equation involve transitions between metastable states separated by high potential barriers. We propose a framework for learning from biased simulations rooted in the infinitesimal generator of the process and the associated resolvent operator.
• Score: 24.560340485988128
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We investigate learning the eigenfunctions of evolution operators for time-reversal invariant stochastic processes, a prime example being the Langevin equation used in molecular dynamics. Many physical or chemical processes described by this equation involve transitions between metastable states separated by high potential barriers that can hardly be crossed during a simulation. To overcome this bottleneck, data are collected via biased simulations that explore the state space more rapidly. We propose a framework for learning from biased simulations rooted in the infinitesimal generator of the process and the associated resolvent operator. We contrast our approach to more common ones based on the transfer operator, showing that it can provably learn the spectral properties of the unbiased system from biased data. In experiments, we highlight the advantages of our method over transfer operator approaches and recent developments based on generator learning, demonstrating its effectiveness in estimating eigenfunctions and eigenvalues. Importantly, we show that even with datasets containing only a few relevant transitions due to sub-optimal biasing, our approach recovers relevant information about the transition mechanism.

Related papers

• Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative Modeling [4.584647857042494]
  Generative models often map noise to data by matching flows or scores, but these approaches become cumbersome for incorporating partial observations or additional priors. Inspired by recent advances in Wasserstein gradient flows, we propose Energy Matching, a framework that unifies flow-based approaches with the flexibility of energy-based models (EBMs) We parameterize this dynamic with a single time-independent scalar field, which serves as both a powerful generator and a flexible prior for effective regularization of inverse problems.
  arXiv  Detail & Related papers  (2025-04-14T18:10:58Z)
• Vibrationally Assisted Exciton Transfer in Open Quantum Systems with Long-Range Interactions [0.0]
  In this work, we use a Frenkel-exciton model with long-range interacting qubits coupled to a damped collective bosonic mode to investigate vibrationally assisted transfer processes. We find that certain delocalized excitonic states maximize the transfer rate and that the entanglement is preserved during the dissipative transfer.
  arXiv  Detail & Related papers  (2025-02-05T19:00:40Z)
• Identifiable Representation and Model Learning for Latent Dynamic Systems [0.0]
  We study the problem of identifiable representation and model learning for latent dynamic systems. We prove that, for linear or affine nonlinear latent dynamic systems, it is possible to identify the representations up to scaling and determine the models up to some simple transformations.
  arXiv  Detail & Related papers  (2024-10-23T13:55:42Z)
• Unsupervised Representation Learning from Sparse Transformation Analysis [79.94858534887801]
  We propose to learn representations from sequence data by factorizing the transformations of the latent variables into sparse components. Input data are first encoded as distributions of latent activations and subsequently transformed using a probability flow model.
  arXiv  Detail & Related papers  (2024-10-07T23:53:25Z)
• Information theory for data-driven model reduction in physics and biology [0.0]
  We develop a systematic approach based on the information bottleneck to identify the relevant variables. We show that in the limit of high compression, the relevant variables are directly determined by the slowest-decaying eigenfunctions. It provides a firm foundation to construct interpretable deep learning tools that perform model reduction.
  arXiv  Detail & Related papers  (2023-12-11T18:39:05Z)
• Learning invariant representations of time-homogeneous stochastic dynamical systems [27.127773672738535]
  We study the problem of learning a representation of the state that faithfully captures its dynamics. This is instrumental to learning the transfer operator or the generator of the system. We show that the search for a good representation can be cast as an optimization problem over neural networks.
  arXiv  Detail & Related papers  (2023-07-19T11:32:24Z)
• Score-based Data Assimilation [7.215767098253208]
  We introduce score-based data assimilation for trajectory inference. We learn a score-based generative model of state trajectories based on the key insight that the score of an arbitrarily long trajectory can be decomposed into a series of scores over short segments.
  arXiv  Detail & Related papers  (2023-06-18T14:22:03Z)
• Learning Functional Transduction [9.926231893220063]
  We show that transductive regression principles can be meta-learned through gradient descent to form efficient in-context neural approximators. We demonstrate the benefit of our meta-learned transductive approach to model complex physical systems influenced by varying external factors with little data.
  arXiv  Detail & Related papers  (2023-02-01T09:14:28Z)
• Particle-Based Score Estimation for State Space Model Learning in Autonomous Driving [62.053071723903834]
  Multi-object state estimation is a fundamental problem for robotic applications. We consider learning maximum-likelihood parameters using particle methods. We apply our method to real data collected from autonomous vehicles.
  arXiv  Detail & Related papers  (2022-12-14T01:21:05Z)
• Provable RL with Exogenous Distractors via Multistep Inverse Dynamics [85.52408288789164]
  Real-world applications of reinforcement learning (RL) require the agent to deal with high-dimensional observations such as those generated from a megapixel camera. Prior work has addressed such problems with representation learning, through which the agent can provably extract endogenous, latent state information from raw observations. However, such approaches can fail in the presence of temporally correlated noise in the observations.
  arXiv  Detail & Related papers  (2021-10-17T15:21:27Z)
• Leveraging Global Parameters for Flow-based Neural Posterior Estimation [90.21090932619695]
  Inferring the parameters of a model based on experimental observations is central to the scientific method. A particularly challenging setting is when the model is strongly indeterminate, i.e., when distinct sets of parameters yield identical observations. We present a method for cracking such indeterminacy by exploiting additional information conveyed by an auxiliary set of observations sharing global parameters.
  arXiv  Detail & Related papers  (2021-02-12T12:23:13Z)
• Nonlinear Independent Component Analysis for Continuous-Time Signals [85.59763606620938]
  We study the classical problem of recovering a multidimensional source process from observations of mixtures of this process. We show that this recovery is possible for many popular models of processes (up to order and monotone scaling of their coordinates) if the mixture is given by a sufficiently differentiable, invertible function.
  arXiv  Detail & Related papers  (2021-02-04T20:28:44Z)
• A Near-Optimal Gradient Flow for Learning Neural Energy-Based Models [93.24030378630175]
  We propose a novel numerical scheme to optimize the gradient flows for learning energy-based models (EBMs) We derive a second-order Wasserstein gradient flow of the global relative entropy from Fokker-Planck equation. Compared with existing schemes, Wasserstein gradient flow is a smoother and near-optimal numerical scheme to approximate real data densities.
  arXiv  Detail & Related papers  (2019-10-31T02:26:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.