Stabilized neural differential equations enforce constraints on dynamical systems.
problem Ensuring dynamical systems preserve known constraints like conservation laws.
method SNDEs with a stabilization term to enforce manifold constraints.
result SNDEs outperform existing methods and broaden constraint types.
Abstract: Defines differential equations in tangent categories, providing conditions for completeness and new perspectives.
problem Defining and working with differential equations in abstract tangent categories.
method Introduces curve objects and dynamical systems, providing conditions for completeness and exploring exponential maps.
result Provides abstract conditions for dynamical systems to be complete and introduces differential exponential rig.
The paper provides a representation for dynamic risk measures and capital allocations.
problem Representation of dynamic risk measures and capital allocations under Itô-Lévy model.
method Representation theorem for dynamic capital allocation derived from BSDEs with quadratic-exponential growth.
result Derivation of a capital allocation representation for dynamic entropic risk measure and static coherent risk measure.
PNDEs project neural dynamics onto constraint manifolds, improving accuracy and stability.
problem Learning dynamics from data without violating known constraints.
method Projecting the learned vector field onto the tangent space of the constraint manifold.
result PNDEs outperform existing methods in learning constrained dynamical systems.
This work extends set-valued risk measures to discrete time, using difference inclusions and equations.
problem Defining set-valued dynamic risk measures in discrete time.
method Investigates discrete time setting with difference inclusions and difference equations.
result Provides insights for continuous time representations of set-valued dynamic risk measures.
Neural differential equations combine deep learning and differential equations for modeling complex systems.
problem Modeling complex systems with high capacity and efficiency.
method Combining neural networks and differential equations, focusing on neural ordinary, controlled, and stochastic differential equations.
result NDEs offer high-capacity function approximation, strong priors, and handle irregular data efficiently.
Relates discrete group actions to orbit spaces as differentiable stacks.
problem Understanding dynamics of discrete groups on manifolds.
method Relating discrete group actions to orbit spaces as differentiable stacks.
result Orbit stack encodes dynamics up to conjugation and inversion.
Neural networks improve predictions of complex network dynamics.
problem Improving neural network predictions for complex network dynamics.
method Extended neural network models to complex systems, ensuring they conform to dynamical model assumptions and using a statistical significance test.
result Achieved advanced generalization of neural network predictions for complex systems.
This paper learns state, dynamics, and filtering algorithms together for data assimilation.
problem Costly parameter tuning and inaccurate dynamics models hinder data assimilation algorithms.
method Auto-differentiable data assimilation framework that learns state, dynamics, and parameters via gradient-based optimization.
result Several data assimilation methods can be learned or tuned within this framework.
Neural GDEs improve graph prediction by blending discrete structures and differential equations.
problem Dynamic graph prediction challenges in irregularly sampled data.
method Continuous-depth graph neural networks (GNNs) with Neural GDEs.
result Neural GDEs enhance performance across various applications.
Graph neural controlled differential equations learn graph dynamics from vertex observations.
problem Predicting future states of dynamical systems on graphs with limited vertex data.
method Incorporates graph topology information into NCDE to predict graph dynamics.
result Informed NCDE requires fewer parameters and lower MAE compared to previous methods.
Graph neural networks are extended to continuous-depth models using differential equations.
problem Improving graph neural networks for static and dynamic graph data.
method Formalizing GNNs as GDEs, blending discrete structures with differential equations.
result GDEs offer computational advantages in static settings and improved performance in dynamic settings.
Differentiable Window improves attention modules by enabling more focused attentions.
problem Improving attention mechanisms in neural networks.
method Proposes Differentiable Window, a neural module for dynamic window selection.
result Consistent and sizable improvements across various NLP tasks.
Study particle dynamics in non-differentiable fractal spaces.
problem Understanding motion in non-smooth, probabilistic geometries.
method Use fiber bundle theory to characterize multivalued geodesic trajectories.
result Developed a hybrid theory combining surface and stochastic process theories.
Smooths dynamic programming for neural networks, improving differentiability.
problem Non-differentiability of dynamic programming algorithms limits their use in neural networks.
method Smooths the max operator in dynamic programming recursion using a strongly convex regularizer, making it differentiable.
result Proposes smoothed dynamic programming operators for sequence prediction and time-series alignment.
JAX MD enables differentiable physics simulations for molecular dynamics.
problem Performing efficient and differentiable physics simulations for molecular dynamics.
method Differentiable physics simulation environments, interaction potentials, neural networks, flexible primitives.
result Differentiable physics simulations can be used for meta-optimization and scaling to large particle systems.
A Gaussian Process Ordinary Differential Equation framework for large continuous dynamical systems
problem Forecasting complex dynamical systems
method Kernel autonomous ODE approach based on Gaussian Processes and Quadratic Order Model Reduction
result Full model outperforms ROM methods in terms of accuracy or computational costs
Bayesian method models spatiotemporal seizure dynamics.
problem Understanding complex seizure dynamics in space and time.
method Bayesian belief updating using variational Laplace in DCM framework.
result Framework assimilates spatial and temporal seizure dynamics.
Lecture notes introduce Abelian differentials and their flat surfaces, focusing on families and Teichmüller dynamics.
problem Study of Abelian differentials and their geometric properties.
method Associate flat surfaces to Abelian differentials and analyze their families under GL2+(R) action. result Properties of orbit of Abelian differentials under Teichmüller dynamics.
Proposes a differentially private bandit algorithm reducing noise over time.
problem Privacy concerns in interactive recommendation systems.
method Tree-based mechanism to add Laplace or Gaussian noise to model parameters, focusing on dynamic global sensitivity.
result Demonstrates (ε,δ)-differential privacy with reduced noise and improved regret. VSDN models sporadic time series with neural SDEs.
problem Modeling irregular and sparse time series data.
method Variational Bayesian method and neural SDEs.
result VSDNs outperform state-of-the-art models in prediction and interpolation.
New dynamical system framework explains Nesterov acceleration.
problem Understanding Nesterov's accelerated gradient method.
method Dynamical system derivation without vanishing step size.
result Acceleration arises from discretizing an ODE with semi-implicit Euler.
Ball-Box Theorem proven for non-differentiable subbundles.
problem Proving a theorem for non-differentiable subbundles.
method Analogue of Ball-Box Theorem for step 2, non-integrable bundles.
result The Ball-Box Theorem holds for a specific class of non-differentiable subbundles.
NeuPDE uses neural networks to model time-dependent data using differential equations.
problem Modeling time-dependent data from dynamic datasets.
method Neural network approach with both shallow multilayer perceptrons and nonlinear differential terms.
result Demonstrated on various dynamical systems, NeuPDE outperforms other methods.
Derives EoM for DNNs to describe GD dynamics precisely.
problem Gaps between differential equations and actual DNN learning dynamics due to discretization error.
method Starts from GF, derives counter term to cancel discretization error, obtains EoM.
result EoM precisely describes GD dynamics of DNNs, highlights differences between continuous and discrete GD.
SINDy-PI robustly identifies implicit dynamics from noisy data.
problem Accurately modeling nonlinear dynamics from noisy data.
method Parallel, implicit SINDy algorithm with multiple optimization algorithms and model selection.
result Significantly more noise robust than previous SINDy approaches.
The volumes of strata of Abelian or quadratic differentials play an important role in the study of dynamics on flat surfaces, related to dynamics in polygonal billiards. This article reviews all known ways to compute volumes in the quadratic case and provides explicit values of volumes of the strata of meromorphic quad…
This thesis attempts to contribute to the study of differentiable dynamics both from a semi-local and global point of view. The center of study is differentiable dynamics in manifolds of dimension 3 where we are interested in the understanding of the existence and structure of attractors as well as dynamical and topolo…
Proposes a method to train neural networks that solve differential equations faster.
problem Training neural networks that solve differential equations becomes computationally expensive.
method Introduces a differentiable surrogate for numerical solver time cost using higher-order derivatives.
result Trains models that are faster to solve while maintaining nearly the same accuracy.
AD-EnKFs use machine learning to improve data assimilation in high-dimensional systems.
problem Data assimilation in high-dimensional, unknown dynamics systems.
method Auto-differentiable ensemble Kalman filters blending machine learning and ensemble Kalman filters.
result AD-EnKFs outperform existing methods in the Lorenz-96 model.
Hybrid model combines neural networks and fluid dynamics for efficient, generalized simulations.
problem Inefficient and poor generalization of deep learning approximations of fluid dynamics.
method Combines graph neural networks with a differentiable PDE solver inside a neural network.
result Hybrid model generalizes well to new scenarios and outperforms both neural network and traditional methods.
Panda predicts chaotic systems without retraining, showing emergent properties.
problem Predicting chaotic systems with small errors.
method Trained on a synthetic dataset of chaotic dynamical systems using evolutionary algorithms.
result Panda predicts unseen chaotic systems with zero-shot learning.
Proposes a deep learning method for modeling dynamic individual-level latent trajectories with changing parameters.
problem Modeling longitudinal data with changing individual-level dynamics parameters.
method Combines deep learning for dimensionality reduction and differential equations for dynamic modeling, allowing different parameters for sub-periods.
result Successfully identifies dynamic parameters and predictors of resilience.
New method infers dynamical systems from population data.
problem Inferring dynamical systems from population data.
method Deducing and estimating Fokker-Planck equation, projecting to test functions, sparse inference.
result Induces driving forces of dynamical systems.
Proposes a stochastic model for limit order book dynamics.
problem Captures the dynamics of limit order books in financial markets.
method Develops a stochastic partial differential equation (SPDE) model with multiplicative noise.
result Shows efficient estimation and computation methods for the model.
Paper proposes a method to verify PINN fidelity using Fisher information from dynamical systems.
problem Quantifying PINN fidelity beyond simple trajectory prediction.
method Employing Fisher information for differentiable dynamical systems to compare PINN's learned equations with analytical models.
result PINN fidelity is verified by matching Fisher information landscapes of learned equations and analytical models.
The paper analyzes convergence of Langevin dynamics with time-dependent metrics.
problem Analyzing convergence of Langevin dynamics with time-dependent metrics.
method Formulated a modified gradient flow of the Kullback-Leibler divergence, selected a time-dependent relative Fisher information functional, and developed a time-dependent Hessian matrix condition.
result Proved convergence conditions for various Langevin dynamics.
Study of influenza A virus spread using mathematical equations.
problem Understanding the spread of influenza A virus infection.
method Mathematical model and analysis of dynamical system.
result Surface trajectories and asymptotic behavior of the system.
Bayesian inference for stochastic differential equations using Wishart diffusions.
problem Inferring stochastic differential equations for regression and dynamical modeling.
method Bayesian non-parametric approach with semi-parametric Wishart processes.
result Modeling diffusion in stochastic differential equations improves performance and avoids overfitting.
Study connects symmetries in dynamical systems to phase plane representations.
problem Understanding symmetries in dynamical systems and their phase plane realizations.
method Analysis of symmetries in differential equations and phase plane representations, establishing correspondence and lifting conditions.
result Every symmetry generator in one formulation corresponds uniquely to a generator in the other, with a lifting condition to solve.
Kernel method approximates dynamical operators from data.
problem Estimating eigenfunctions of dynamical operators from data.
method Kernel-based approach in reproducing kernel Hilbert spaces.
result Eigenfunctions estimated via matrix eigenvalue problems.
Study uses machine learning to predict predator-prey dynamics without prior knowledge.
problem Predicting predator-prey interactions without prior knowledge of the system.
method Applied Neural Ordinary Differential Equations (Neural ODEs) and Universal Differential Equations (UDEs) to the Lotka-Volterra model.
result UDEs outperform Neural ODEs in predicting predator-prey dynamics, especially in noisy data.
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.
Realizations of stochastic process are often observed temporal data or functional data. There are growing interests in classification of dynamic or functional data. The basic feature of functional data is that the functional data have infinite dimensions and are highly correlated. An essential issue for classifying dyn…
The paper proves properties of strata of differentials, showing they are affine and extremal.
problem Properties of strata of differentials, particularly their geometry and tautological rings.
method Analyzing the tautological rings and using Teichmüller dynamics to prove properties.
result Strata of differentials are affine and their stratification is extremal.
This paper is an attempt at understanding the quantum-like dynamics of financial markets in terms of non-differentiable price-time continuum having fractal properties. The main steps of this development are the statistical scaling, the non-differentiability hypothesis, and the equations of motion entailed by this hypot…
The paper proves metrizability and dynamics of Weil bundles.
problem Metrizability and dynamics of Weil bundles in differential geometry.
method Investigation of metrizability and dynamics of Weil bundles for smooth compact manifolds and Weil algebras.
result A canonical, complete, weighted metric \(\mathfrak{d}_w\) on \(M^\mathbf{A}\) that encodes geometry and deformations.
Researchers use statistical physics to model neural network learning dynamics.
problem Understanding the learning dynamics of ReLU neural networks.
method Developed a system of differential equations using statistical physics techniques.
result ReLU networks exhibit distinct learning behavior compared to sigmoidal networks.