Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

68136203271 · Jun 202019922001200920172026
48 results for Ordinary Differential Equations (ODEs)

NP-ODE models FEA simulations with uncertainty, improving accuracy and efficiency.

problem Limitations of FEA in terms of computational cost and uncertainty quantification.
method Physics-informed neural process aided ordinary differential equations (NP-ODE).
result NP-ODE outperforms benchmark methods in uncertainty quantification and prediction accuracy.

The goal of the present paper is to propose an enhanced ordinary differential equations solver by exploitation of the powerful equivalence method of Élie Cartan. This solver returns a target equation equivalent to the equation to be solved and the transformation realizing the equivalence. The target ODE is a member of …

2007-11-30abs ↗pdf ↗

This paper uses ODE to improve RNN models for time series data.

problem Improving RNN models for irregularly sampled time series data.
method Extending RNNs with Neural Ordinary Differential Equations (ODEs).
result New ODE-based RNN models reduce training and evaluation time.

The paper solves the equivalence problem for a specific class of ODEs.

problem Solving the equivalence problem for a specific class of ordinary differential equations.
method Construction of the algebra of differential invariants for point transformations.
result The equivalence problem is solved for the given class of ODEs.

Generalization bounds derived for neural ODEs and deep residual networks.

problem Understanding the generalization capability of neural ODEs and deep residual networks.
method Lipschitz-based argument and analogy with deep residual networks.
result A generalization bound involving the magnitude of weight matrix differences.

Steerable neural ODEs on homogeneous spaces for equivariant feature dynamics.

problem Learning continuous-time equivariant dynamics of vector-valued features on homogeneous spaces.
method Introduces steerable neural ordinary differential equations on homogeneous spaces, interpreting features as sections of associated vector bundles over MM.
result Steerable NODEs are GG-equivariant when the flow and connection are GG-invariant, and they incorporate existing models.

These are lecture notes of the Summer school on the geometry of differential equations held in Nordfjordeid, Norway in 1996. They cover geometric structures related to scalar second order ODEs, the construction of the associated Cartan connection, techniques for computing invariants of differential equations starting f…

2016-02-02abs ↗pdf ↗

PINNs struggle with increasingly complex ODEs, especially when parameters control their complexity.

problem Evaluating physics-informed neural networks on complex coupled ODEs.
method Tuned benchmarks of partial differential equations and harmonic oscillators; varying network architecture and training method.
result PINNs fail to solve complex ODEs, revealing issues like insufficient capacity, poor conditioning, and high local curvature.

DALTON improves ODE parameter estimation by learning from noisy data.

problem High sensitivity to parameters in ODEs produces unreliable parameter estimates.
method Data-adaptive probabilistic likelihood approximation for ODEs.
result DALTON produces more accurate parameter estimates than existing methods.

We show that Neural Ordinary Differential Equations (ODEs) learn representations that preserve the topology of the input space and prove that this implies the existence of functions Neural ODEs cannot represent. To address these limitations, we introduce Augmented Neural ODEs which, in addition to being more expressive…

2019-04-02abs ↗pdf ↗

We solve the local equivalence problem for second order (smooth or analytic) ordinary differential equations. We do so by presenting a {\em complete convergent normal form} for this class of ODEs. The normal form is optimal in the sense that it is defined up to the automorphism group of the model (flat) ODE y"=0y"=0. For…

2016-11-25abs ↗pdf ↗

New symmetries found for scalar and vector ODEs of arbitrary dimensions.

problem Identifying symmetries for scalar and vector ODEs of arbitrary dimensions.
method Explicit expressions and abelian Lie algebra for non-Cartan symmetries in arbitrary dimensions.
result Non-Cartan symmetries characterize linearizable systems of ODEs but not nonlinear ones.

We describe a set of Gaussian Process based approaches that can be used to solve non-linear Ordinary Differential Equations. We suggest an explicit probabilistic solver and two implicit methods, one analogous to Picard iteration and the other to gradient matching. All methods have greater accuracy than previously sugge…

2014-08-17abs ↗pdf ↗

Neural controlled DEs model irregular time series by adjusting based on observations.

problem Modeling irregularly sampled multivariate time series with memory-efficient adjoint-based backpropagation.
method Neural controlled differential equations (CDEs) that adjust based on subsequent observations.
result Achieves state-of-the-art performance on various datasets.

Continuous-depth Evoformer reduces protein folding prediction time and resource usage.

problem Efficient protein structure prediction with reduced computational costs.
method Continuous-depth formulation of Evoformer using Neural Ordinary Differential Equations (Neural ODEs).
result The continuous-time Evoformer achieves constant memory cost and improved efficiency.

Neural Laplace models diverse DEs in the Laplace domain for better dynamics.

problem Inadequate ODEs for long-range dependencies and discontinuities.
method Unified framework in Laplace domain, using stereographic map for smoothness.
result Superior performance in diverse DEs, including complex history dependency and abrupt changes.

Deep ResNets exhibit distinct scaling properties with depth, challenging neural ODE models.

problem Understanding the scaling properties of deep ResNets and their relation to neural ODEs.
method Detailed numerical experiments on weights trained by stochastic gradient descent.
result Deep ResNets can exhibit different scaling regimes, including stochastic differential equations or neither, challenging the neural ODE model.

New method combines ODE solvers with Bayesian inference for efficient model training.

problem Combining ODE solvers with Bayesian inference for efficient model training.
method Probabilistic state space model using extended Kalman filter for joint inference from differential equations and data.
result Efficient approximate Bayesian inference on latent force and ODE solution.

New methods prove existence of rotating shapes moving in space.

problem Existence of rotating shapes moving in space.
method Different methods to prove existence based on singular ordinary differential equation.
result Existence of rotationally symmetric translating solutions proven without partial differential equations.

The study identifies exceptions to fiber-preserving symmetry in ODEs and systems.

problem Identifying exceptions to fiber-preserving symmetry in ODEs and systems.
method Lie's classification of Lie algebras of vector fields, absolute and relative scalar differential invariants, conditional and vector-valued relative invariants, prolongations of actions.
result Examples of scalar ODEs and systems with symmetry groups not fiber-preserving.

Generative model uses ODEs and RKHSs for measure matching.

problem Minimum divergence generative modeling and sampling.
method Diffeomorphic matching and image registration principles applied to ODEs and RKHSs.
result Theoretical error bounds and extensive numerical experiments demonstrate the method's properties and applicability.

Novel method for solving ODEs on k-polysymplectic manifolds.

problem Solving ordinary differential equations on k-polysymplectic manifolds.
method k-polysymplectic energy-momentum method.
result Novel stability analysis techniques applied to Hamiltonian systems.

Investigates the relationship between ResNets and Neural ODEs, quantifying their closeness and providing training methods.

problem Quantifying the distance between ResNet dynamics and Neural ODE solutions.
method Bounding the distance between hidden state trajectories and Neural ODE solutions, using gradient descent and Heun's method.
result Gradient descent and Heun's method can implicitly regularize ResNets towards Neural ODEs, especially for smooth residual functions.

Time series with non-uniform intervals occur in many applications, and are difficult to model using standard recurrent neural networks (RNNs). We generalize RNNs to have continuous-time hidden dynamics defined by ordinary differential equations (ODEs), a model we call ODE-RNNs. Furthermore, we use ODE-RNNs to replace t…

2019-07-08abs ↗pdf ↗