Homogeneous magnetic trajectories in a special linear group proven.
problem Proving homogeneity of magnetic trajectories in a specific group.
method Using contact magnetic curves and geodesics.
result Every contact magnetic trajectory is a product of a homogeneous geodesic and a charged Reeb flow.
Study trajectories on homothety surfaces, linking to square torus and revealing mixed behaviors.
problem Analyzing linear trajectories on homothety surfaces.
method Examined a 1-parameter family of genus-2 homothety surfaces, considering their linear trajectories and their relation to square torus.
result Trajectories on homothety surfaces can contain either a closed loop or a lamination with Cantor cross-section, and their cutting sequences are either periodic or Sturmian.
The paper proves that linearization along trajectories preserves flatness in discrete-time systems.
problem The relation between nonlinear and linear time-varying systems.
method Linearization along trajectories of a flat discrete-time system.
result The linearized system is flat, and a flat output can be derived.
We learn linear models from nonlinear systems using multiple trajectories and regularization.
problem Identifying linear models from data when the underlying dynamics are nonlinear.
method Multiple trajectories data acquisition followed by regularized least squares.
result Learn linearized dynamics with arbitrarily small error given enough samples.
Robots learn movement libraries by segmenting complex trajectories.
problem Segmenting complex robot movement demonstrations for library building.
method Model trajectories as Switching Linear Dynamical Systems and infer segmentation using a nonparametric Bayesian approach.
result Robots can learn movement libraries more effectively by segmenting demonstrations.
Study learns dynamics of linear systems from multiple short trajectories.
problem Learning dynamics of autonomous linear systems from multiple short trajectories.
method Finite sample analysis for stable and unstable systems, adjusting trajectory length for marginally stable systems.
result Learning rate of O ( 1 N ) \mathcal{O}(\frac{1}{\sqrt{N}}) O ( N 1 ) for both stable and unstable systems. The paper provides a non-asymptotic error bound for linear system identification under nonlinear policies.
problem System identification for linear systems with nonlinear and/or time-varying policies under i.i.d. random excitation noises.
method Least square estimation with non-asymptotic error bound for bounded state and action trajectories.
result The error bound is consistent with linear policies and generalizes existing guarantees.
Paper analyzes EM algorithm's trajectory in 2MLR, revealing cycloid behavior.
problem Understanding the convergence and trajectory of EM algorithm in 2MLR.
method Explicit closed-form expressions for EM updates, recurrence relation derivation at population level.
result EM iterations lie on a cycloid trajectory, leading to theoretical estimate of convergence exponent.
Improved Gaussian Process model for predicting trajectories without independence assumption errors.
problem Incorrect independence assumption in previous work on Gaussian Process uncertainty propagation.
method Proposed a novel piecewise linear approximation to correct the independence assumption in continuous models.
result Corrected the independence assumption in Gaussian Process models for predicting trajectories.
The paper provides guarantees for learning switching non-linear systems from a single trajectory.
problem Learning non-linear dynamical systems with switching dynamics.
method Non-asymptotic bounds derived under stability assumptions for i.i.d. switching modes.
result Explicit convergence rates for Hölder and linear function classes based on effective sample size.
Study of supervised learning from multiple non-independent sequences.
problem Efficient learning from many non-independent sequences.
method Generalizes conditions for efficient learning from independent examples and single auto-correlated sequences.
result Error rate changes from Θ ( n / m T ) Θ(n / m T) Θ ( n / m T ) to Ω ( n 2 / m 2 T ) Ω(n^2 / m^2 T) Ω ( n 2 / m 2 T ) as the number of trajectories increases. Algorithm learns mixtures of Markov chains and MDPs from short trajectories.
problem Learning mixtures of Markov chains and MDPs from short unlabeled trajectories.
method Subspace estimation, spectral clustering, EM algorithm, model estimation, classification.
result 96.6% average accuracy on a mixture of two MDPs in gridworld, outperforming EM algorithm with random initialization.
Trajectory data suffices for efficient RL in linear MDPs.
problem Efficient offline RL in linear MDPs without state space scaling.
method Linear MDP approximation and trajectory data.
result Trajectory data suffices for deriving ε-optimal policies.
We study the existence of closed trajectories of a particle model on null curves in anti-de Sitter 3-space defined by a functional which is linear in the curvature of the particle path. Explicit expressions for the trajectories are found and the existence of infinitely many closed trajectories is proved.
New method improves learning from multiple correlated data trajectories.
problem Learning from multiple correlated data trajectories without mixing assumptions.
method Hellinger localization framework for maximum likelihood estimation.
result Instance-optimal bounds that scale with full data budget under broad conditions.
A neural network learns to control a two-link arm with non-linear dynamics.
problem Training spiking neural networks to control complex, non-linear systems.
method Feedback-based Online Local Learning Of Weights (FOLLOW) to train a network of spiking neurons with hidden layers.
result The network learns an inverse model of the arm's dynamics and uses it to generate a motor command for control.
Estimates MLDS using tensor decomposition, improving upon existing methods.
problem Learning mixtures of linear dynamical systems from input-output data.
method Proposes a moment-based estimator using tensor decomposition.
result Improves sample complexity bounds for estimating MLDS.
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…
End-to-end framework optimizes constrained trajectories using data-driven methods.
problem Optimizing trajectories under constraints with limited dynamics knowledge.
method Data-driven approach decomposes trajectories into function basis, uses maximum a posteriori for optimization, and incorporates linear constraints.
result Commanding results in aeronautics and sailing route optimization.
We identify linear models from nonlinear systems with initialization constraints.
problem Identifying linear models from nonlinear systems with initialization constraints.
method Multiple trajectories-based deterministic data acquisition algorithm followed by regularized least squares.
result We provide a finite sample error bound on the learned linearized dynamics.
Optimal execution of portfolio transactions is the essential part of algorithmic trading. In this paper we present in simple analytical form the optimal trajectory for risk-averse trader with the assumption of exponential market recovery and short-time investment horizon.
Algorithm learns multiple LDS models from unlabeled short trajectories.
problem Learning from unlabeled short sample trajectories of multiple LDS models.
method Two-stage meta-algorithm with end-to-end performance guarantees.
result Efficiently recovers each ground-truth LDS model up to error i l d e O ( d / T ) ilde{O}(\sqrt{d/T}) i l d e O ( d / T ) . The paper defines and analyzes conformal trajectories in 3D space forms.
problem Understanding trajectories in curved 3D spaces.
method Defined conformal trajectories and studied their properties in R 3 {\mathbb{R}}^3 R 3 , S 3 {\mathbb{S}}^3 S 3 , and H 3 {\mathbb{H}}^3 H 3 . result Conformal trajectories in S 3 {\mathbb{S}}^3 S 3 and H 3 {\mathbb{H}}^3 H 3 have constant curvature and torsion. Develops an oblique projection technique to approximate a foliation for non-normal dynamics.
problem Modeling dynamics far from a primary Spectral Submanifold (SSM) in non-normal systems.
method Oblique projection technique based on experimental data.
result Approximates a stable invariant foliation for non-normal dynamics efficiently.
Geometric analysis shows gradient descent in linear neural nets converges to global minima.
problem Analyzing convergence of gradient descent in linear neural networks.
method Geometric framework and invariance property of network structure.
result Gradient descent trajectories converge to global minima for linear neural nets.
Improved trajectory prediction for team sports using sparse outputs.
problem Challenging to train deep learning models for player trajectory prediction.
method Sparse trajectory prediction and constant acceleration interpolation.
result Interpolation improves performance for all tested models.
New method for IRL with missing data.
problem Recovering reward function with missing data.
method Direct computation of log-likelihood with linear equations.
result Efficient handling of missing segments in trajectories.
New method efficiently evaluates policies using trajectory data.
problem Statistically efficient policy evaluation with limited data.
method Trajectory-based approach for policy evaluation.
result Improved sample complexity for policy evaluation.
Diagonal linear networks converge to lasso regularization path during training.
problem Understanding the regularization behavior of diagonal linear networks.
method Analyzing the training trajectory of diagonal linear networks and comparing it to the lasso regularization path.
result The training trajectory of diagonal linear networks is closely related to the lasso regularization path.
Paper proposes a method for optimizing local policies for trajectory-centric reinforcement learning.
problem Challenges in global policy optimization for non-linear systems and poor performance of open-loop trajectory optimization.
method Formulates trajectory optimization and local policy synthesis as a single optimization problem and solves it as a nonlinear programming instance.
result Demonstrates improved performance of the proposed technique under simplifying assumptions.
Cohen et al. (2021) show GD trajectories align on a bifurcation diagram.
problem Understanding the Edge of Stability (EoS) phenomenon in gradient descent.
method Empirical studies and rigorous mathematical proofs for two-layer networks and single-neuron networks.
result GD trajectories align on a specific bifurcation diagram independent of initialization.
The paper shows how data and algorithm interactions affect overparameterized linear regression generalization.
problem Understanding generalization in overparameterized linear regression.
method Introducing data-algorithm compatibility and performing data-dependent trajectory analysis with gradient descent.
result Early stopping iterates lead to better generalization than last-iterate analysis, with weaker restrictions.
Extended Kalman Filter is shown to be a gradient descent in trajectory space.
problem Estimating state of dynamical systems from noisy measurements.
method Recovery of extended Kalman filter equations from Amari's natural gradient in trajectory space.
result Extended Kalman Filter is equivalent to natural gradient descent in trajectory space.
LRF framework predicts and interprets longitudinal response trajectories.
problem Sparse and irregular data in longitudinal studies.
method Longitudinal Random Forest (LRF) framework with adaptive node-wise trajectory estimation.
result LRF outperforms competing methods in predicting and interpreting longitudinal trajectories.
Develops MENT for interpreting and detecting changes in network trajectories.
problem Distortion of network geometry and invalidation of temporal comparisons in dynamic network analysis.
method Develops Multiscale Euclidean Network Trajectories (MENT) framework based on second-moment geometry.
result Validates and interprets network trajectories through isotropic normalization and orthogonal transformations.
We propose a minimal theory of non-linear price impact based on a linear (latent) order book approximation, inspired by diffusion-reaction models and general arguments. Our framework allows one to compute the average price trajectory in the presence of a meta-order, that consistently generalizes previously proposed pro…
OLS estimator nearly optimally identifies linear systems from single trajectory.
problem Identifying linear dynamical systems from a single observed trajectory.
method Generalized small-ball method for dependent data, avoiding mixing-time arguments.
result OLS estimator nearly matches minimax optimal performance for linear systems.
MoNODEs improve neural ODEs by separating dynamic states from static factors.
problem Learning non-linear dynamics with variations across trajectories.
method Introduces time-invariant modulator variables to separate dynamic states from static factors.
result Consistently improves model generalization and far-horizon forecasting.
Reasoning models generate differently based on problem difficulty, not just length.
problem Understanding how reasoning models handle different problem difficulties.
method Examined hidden-state trajectories across competitive programming, mathematics, and Boolean satisfiability.
result Corrected trajectory geometry shows difficulty-dependent differences in reasoning models, with stronger effects in the code domain.
Many real-valued stochastic time-series are locally linear (Gassian), but globally non-linear. For example, the trajectory of a human hand gesture can be viewed as a linear dynamic system driven by a nonlinear dynamic system that represents muscle actions. We present a mixed-state dynamic graphical model in which a hid…
The paper introduces a new method to assess system stability using torsion of state trajectories.
problem Stability assessment of linear time-invariant systems.
method Using the torsion τ ( t ) τ(t) τ ( t ) of the state trajectory to determine stability. result Conditions for stability and asymptotic stability are established based on the behavior of torsion.
Algorithm learns weight matrix from single trajectory of nonlinear dynamical system.
problem Learning weight matrix from a single trajectory of nonlinear dynamical system.
method Algorithm uses global stability and well-conditioned covariance to recover weight matrix.
result Algorithm recovers weight matrix with optimal sample complexity and linear running time.
MOCK learns complex systems from trajectories efficiently.
problem Learning nonparametric differential equations from high-dimensional data.
method MOCK uses multivariate occupation kernel functions to learn vector fields linearly.
result MOCK outperforms other methods on various datasets.
New metric shows how different regularization methods affect deep linear networks.
problem Understanding the training dynamics of deep linear networks.
method Introduced a new metric called layer imbalance to analyze training dynamics. Demonstrated behavior of different regularization methods and stochastic gradient descent.
result Different regularization methods behave similarly, leading to a flat minima.
This work proposes a new algorithm for efficient reduced modeling of non-linear dynamical systems.
problem Reduced modeling of computationally demanding dynamical systems to balance accuracy and complexity.
method Embedding trajectories in a RKHS, solving low-rank constraint optimization problems, and exploiting kernel-based computations.
result The proposed algorithm achieves a gain in approximation accuracy and computational efficiency.
This work enables UAVs to autonomously form desired trajectories without needing a central plan.
problem Autonomous formation of complex trajectories in UAVs.
method Decentralized control system using geometric embeddings.
result Quadcopters self-organize into desired trajectories while maintaining separation.
Proposes a method to estimate SDE noise from a single trajectory.
problem Estimating SDE noise from a single data trajectory without ergodicity or stationarity.
method Combining Taylor expansions, Girsanov transformations, and drift function's initial value for drift and noise estimation.
result First SSISDE algorithm capable of identifying SDE dynamics from a single trajectory.
Single trajectory learns LTI system realization.
problem Learning LTI system realization from a single trajectory.
method Finite time analysis of Markov parameters, Ho-Kalman algorithm stability, sample complexity.
result Data needed for accurate balanced realization learning.