arXiv research

New method learns behavioral representations from mobility data.

A new neural network captures and explains trajectory patterns.

A method for representing and comparing categorical trajectories using multivariate functional principal components.

Reasoning models generate differently based on problem difficulty, not just length.

Visual observations of dynamic phenomena, such as human actions, are often represented as sequences of smoothly-varying features . In cases where the feature spaces can be structured as Riemannian manifolds, the corresponding representations become trajectories on manifolds. Analysis of these trajectories is challengin…

Study learns dynamics of linear systems from multiple short trajectories.

This work characterizes how data augmentation shapes neural representations.

Paper analyzes EM algorithm's trajectory in 2MLR, revealing cycloid behavior.

This work presents a methodology to design trajectory tracking feedback control laws, which embed non-parametric statistical models, such as Gaussian Processes (GPs). The aim is to minimize unmodeled dynamics such as undesired slippages. The proposed approach has the benefit of avoiding complex terramechanics analysis …

The paper proposes a deep generative model for complex disease trajectories.

Paper proposes a method for optimizing local policies for trajectory-centric reinforcement learning.

TRAKNN detects rare atmospheric trajectories efficiently.

We learn linear models from nonlinear systems using multiple trajectories and regularization.

Cohen et al. (2021) show GD trajectories align on a bifurcation diagram.

Reinforcement learning with trajectory feedback instead of state-action rewards.

DETECT clusters mobility behaviors from trajectories using deep learning.

Transportation agencies have an opportunity to leverage increasingly-available trajectory datasets to improve their analyses and decision-making processes. However, this data is typically purchased from vendors, which means agencies must understand its potential benefits beforehand in order to properly assess its value…

The paper proposes a new method for clustering survival data using smoothed log-hazard trajectories.

The problem of continuous inverse optimal control (over finite time horizon) is to learn the unknown cost function over the sequence of continuous control variables from expert demonstrations. In this article, we study this fundamental problem in the framework of energy-based model, where the observed expert trajectori…

Develops a method to infer cell trajectories from RNA sequencing data.

New method detects metastable basins in high dimensions using trajectory sampling.

Develops MENT for interpreting and detecting changes in network trajectories.

Adaptive optimization methods bias neural network trajectories towards regions of lower local geometry.

Generative model for SSc disease trajectories using deep learning.

Car following models have been widely applied and made remarkable achievements in traffic engineering. However, the traffic micro-simulation accuracy of car following models in a platoon level, especially during traffic oscillations, still needs to be enhanced. Rather than using traditional individual car following mod…

The study analyzes optimization trajectories in neural networks to reveal redundancy and redundancy-reducing strategies.

Proposes SSC for estimating counterfactual survival trajectories from observational data.

TraLFM models human mobility patterns from traffic trajectories.

The paper shows how data and algorithm interactions affect overparameterized linear regression generalization.

Mathematical method based on a direct or indirect analysis of growth rates is described. It is shown how simple assumptions and a relatively easy analysis can be used to describe mathematically complicated trends and to predict growth. Only rudimentary knowledge of calculus is required. Projected trajectories based on …

We introduce a generative adversarial network (GAN) model to simulate the 3-dimensional Lagrangian motion of particles trapped in the recirculation zone of a buoyancy-opposed flame. The GAN model comprises a stochastic recurrent neural network, serving as a generator, and a convoluted neural network, serving as a discr…

New analysis shows FM learns underlying dynamical structure, not just trajectory replay.

Modeling continuous movement of entities in latent space for interaction timing.

The paper explores states of financial markets using correlation matrices and their dynamics.

Study of supervised learning from multiple non-independent sequences.

Infants with a variety of complications at or before birth are classified as being at risk for developmental delays (AR). As they grow older, they are followed by healthcare providers in an effort to discern whether they are on a typical or impaired developmental trajectory. Often, it is difficult to make an accurate d…

A method for inferring motility models and heterogeneity from particle trajectories.

This paper compares machine learning methods for recognizing lane change intentions from vehicle trajectories.

Novel methods improve Bayesian analysis of chaotic dynamical systems.

Predicting transportation modes from GPS (Global Positioning System) records is a hot topic in the trajectory mining domain. Each GPS record is called a trajectory point and a trajectory is a sequence of these points. Trajectory mining has applications including but not limited to transportation mode detection, tourism…

DDD reformulated for sparse matrices, integrating trajectory and snapshot time series data.

LLMs learn probability density functions in-context, showing distinct learning trajectories.

We revisit the stochastic variance-reduced policy gradient (SVRPG) method proposed by Papini et al. (2018) for reinforcement learning. We provide an improved convergence analysis of SVRPG and show that it can find an $ε$-approximate stationary point of the performance function within $O(1/ε^{5/3})$ trajectories. This s…

New method efficiently evaluates policies using trajectory data.

Podcast recommendations improved by analyzing user listening paths.

Proposes a model for generating survival trajectories and data.

The paper provides a non-asymptotic error bound for linear system identification under nonlinear policies.

New algorithm speeds up RNN time series prediction by filtering noise.