Trajectory inference via Acceleration Matching

• URL: http://arxiv.org/abs/2608.03916v1
• Date: Tue, 04 Aug 2026 16:42:04 GMT
• Title: Trajectory inference via Acceleration Matching
• Abstract summary: We propose a new algorithm called Acceleration Matching (textttAM)<n>Our approach consists of lifting the original problem to phase space and then regressing onto an explicit conditional acceleration field that induces random, smooth trajectories.<n>Our resulting training algorithm only requires positional data, avoids trajectory simulation during training, and is devoid of expensive preprocessing.<n>We provide ample numerical evidence suggesting that textttAM is competitive with or superior to existing algorithms on several benchmark problems from the existing literature.
• Score: 17.67414145245464
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Trajectory inference is a fundamental problem in many scientific domains: given a collection of unpaired snapshots of observations at discrete time points, the goal is to generate smooth trajectories that best resemble and interpolate the data. Existing algorithms exhibit computational challenges: they either rely on preprocessing subroutines to enforce smoothness or on simulation-based training objectives, both of which can be expensive. In order to overcome these limitations, we propose a new algorithm called Acceleration Matching (\texttt{AM}). Our approach consists of lifting the original interpolation problem to phase space and then regressing onto an explicit conditional acceleration field that induces random, smooth trajectories that agree with the prescribed marginals. Importantly, our resulting training algorithm only requires positional data, avoids trajectory simulation during training, and is devoid of expensive preprocessing. We provide ample numerical evidence suggesting that \texttt{AM} is competitive with or superior to existing algorithms on several benchmark problems from the existing literature.

Related papers

• Multi-Marginal Flow Matching with Adversarially Learnt Interpolants [27.294164408278448]
  This paper proposes a novel flow matching method that overcomes the limitations of existing multi-marginal trajectory inference algorithms.<n>Our proposed method, ALI-CFM, uses a GAN-inspired adversarial loss to fit neurally parametrised interpolant curves between source and target points.<n>We showcase the versatility and scalability of our method by outperforming the existing baselines on spatial transcriptomics and cell tracking datasets.
  arXiv  Detail & Related papers  (2025-10-01T17:47:27Z)
• Single-loop Algorithms for Stochastic Non-convex Optimization with Weakly-Convex Constraints [49.76332265680669]
  This paper examines a crucial subset of problems where both the objective and constraint functions are weakly convex.<n>Existing methods often face limitations, including slow convergence rates or reliance on double-loop designs.<n>We introduce a novel single-loop penalty-based algorithm to overcome these challenges.
  arXiv  Detail & Related papers  (2025-04-21T17:15:48Z)
• Effectively Leveraging Momentum Terms in Stochastic Line Search Frameworks for Fast Optimization of Finite-Sum Problems [1.5665889790660235]
  We explore the relationship between recent line search approaches for deep optimization and momentum directions.<n>We introduce an algorithmic framework that exploits a mix of data persistency, persistient type rules for definition of the momentum parameter and line searches.<n>The resulting algorithm provably possesses convergence under suitable assumptions.
  arXiv  Detail & Related papers  (2024-11-11T16:26:33Z)
• Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling [34.853443523585604]
  We propose a variational formulation of Doob's h-transform as an optimization problem over trajectories between a given initial point and the desired ending point.<n>Our approach significantly reduces the search space over trajectories and avoids expensive trajectory simulation.<n>We demonstrate the ability of our method to find feasible transition paths on real-world molecular simulation and protein folding tasks.
  arXiv  Detail & Related papers  (2024-10-10T14:32:16Z)
• Accelerated First-Order Optimization under Nonlinear Constraints [61.98523595657983]
  We exploit between first-order algorithms for constrained optimization and non-smooth systems to design a new class of accelerated first-order algorithms.<n>An important property of these algorithms is that constraints are expressed in terms of velocities instead of sparse variables.
  arXiv  Detail & Related papers  (2023-02-01T08:50:48Z)
• The Neural Network shifted-Proper Orthogonal Decomposition: a Machine Learning Approach for Non-linear Reduction of Hyperbolic Equations [0.0]
  In this work we approach the problem of automatically detecting the correct pre-processing transformation in a statistical learning framework. The purely data-driven method allowed us to generalise the existing approaches of linear subspace manipulation to non-linear hyperbolic problems with unknown advection fields. The proposed algorithm has been validated against simple test cases to benchmark its performances and later successfully applied to a multiphase simulation.
  arXiv  Detail & Related papers  (2021-08-14T15:13:35Z)
• Resource Allocation in Multi-armed Bandit Exploration: Overcoming Sublinear Scaling with Adaptive Parallelism [107.48538091418412]
  We study exploration in multi-armed bandits when we have access to a divisible resource that can be allocated in varying amounts to arm pulls. We focus in particular on the allocation of distributed computing resources, where we may obtain results faster by allocating more resources per pull.
  arXiv  Detail & Related papers  (2020-10-31T18:19:29Z)
• Activation Relaxation: A Local Dynamical Approximation to Backpropagation in the Brain [62.997667081978825]
  Activation Relaxation (AR) is motivated by constructing the backpropagation gradient as the equilibrium point of a dynamical system. Our algorithm converges rapidly and robustly to the correct backpropagation gradients, requires only a single type of computational unit, and can operate on arbitrary computation graphs.
  arXiv  Detail & Related papers  (2020-09-11T11:56:34Z)
• Single-Timescale Stochastic Nonconvex-Concave Optimization for Smooth Nonlinear TD Learning [145.54544979467872]
  We propose two single-timescale single-loop algorithms that require only one data point each step. Our results are expressed in a form of simultaneous primal and dual side convergence.
  arXiv  Detail & Related papers  (2020-08-23T20:36:49Z)
• Accelerated Message Passing for Entropy-Regularized MAP Inference [89.15658822319928]
  Maximum a posteriori (MAP) inference in discrete-valued random fields is a fundamental problem in machine learning. Due to the difficulty of this problem, linear programming (LP) relaxations are commonly used to derive specialized message passing algorithms. We present randomized methods for accelerating these algorithms by leveraging techniques that underlie classical accelerated gradient.
  arXiv  Detail & Related papers  (2020-07-01T18:43:32Z)

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.