New method learns PDE solutions from low-fidelity data.
problem Challenges in learning PDE surrogates with scarce data.
method Flow matching in infinite-dimensional space with conditional neural operators.
result Accurately learns PDE solutions across different resolutions and fidelities.
The paper proposes a method to sample quantum field configurations using neural operators and flows.
problem Sampling lattice field configurations from Boltzmann distributions in quantum field theories.
method Approximating a time-dependent neural operator to map between free and target theories, discretizing to a normalizing flow, and training to diffeomorphism.
result The method can generalize to larger lattice sizes when pre-trained on smaller ones, improving efficiency.
We present a particle flow realization of Bayes' rule, where an ODE-based neural operator is used to transport particles from a prior to its posterior after a new observation. We prove that such an ODE operator exists. Its neural parameterization can be trained in a meta-learning framework, allowing this operator to re…
Develops a new method for functional regression that works with non-Gaussian data.
problem Limited models for regression in function spaces with Gaussian process priors.
method Introduces Neural Operator Flows (OpFlow) for non-Gaussian function spaces.
result OpFlow enables robust and accurate uncertainty quantification for functional regression.
HFNO enhances interpretability of turbulent flows through parallel wavenumber bin processing.
problem Opaque inner workings of Fourier Neural Operators (FNOs) hinder physical interpretability.
method Introduces HFNO, a novel FNO-based architecture that processes wavenumber bins in parallel, enhancing interpretability.
result HFNO decomposes turbulent flows across various scales, enabling increased interpretability and multiscale modeling.
Develops a smooth operator framework for analyzing neural network representations.
problem Analyzing the geometry of feedforward neural network representations.
method Introduces a smooth operator-theoretic approach based on diffusion Markov operators derived from feature clouds.
result Establishes a stable operator-geometric framework for tracking training, width, and perturbation stability.
Physics-guided neural network improves power flow analysis.
problem Infeasibility of traditional numerical approaches due to outdated or unavailable PF equations.
method Proposes a physics-guided neural network to learn PF mappings from historical data while constraining by physical laws.
result Physics-guided neural network achieves better performance and generalizability than unconstrained data-driven approaches.
Deep neural network approximates flow averages for rough walls in multiscale simulations.
problem Approximating flow averages in rough-wall Stokes flow simulations.
method Fourier neural operator for local averages, parameterized by local wall geometry.
result Stable and accurate HMM solution with reduced micro problem solving cost.
GATES improves neural architecture search by modeling operations as information transformation.
problem Improving predictor-based neural architecture search efficiency.
method GATES models operations as information transformation, covering both node and edge cell search spaces.
result GATES boosts sample efficiency and improves predictor performance.
Novel neural operator predicts complex spatiotemporal dynamics from partial observations.
problem Capturing complex operator dynamics in infinite-dimensional function spaces.
method Integrates Koopman operator theory with deep neural networks to approximate nonlinear operators between Banach spaces.
result BNO achieves robust zero-shot super-resolution in unsteady flow prediction and outperforms conventional methods.
New algorithms improve vascular flow simulations in aortic aneurysms.
problem Limited accuracy of MRI in hemodynamics, patient-specific flow boundary conditions, and CFD's computational demands.
method Physics-Informed Neural Networks (PINNs) and Deep Operator Networks (DeepONets) integrated with 3D Navier-Stokes equations.
result Improved computational efficiency and good agreement with CFD simulations.
PILNO uses neural operators to solve PDEs efficiently on point clouds.
problem Solving partial differential equations (PDEs) on point cloud data efficiently.
method Physics-informed low-rank neural operator framework combining low-rank kernel approximations and an encoder-decoder architecture.
result PILNO efficiently approximates solution operators of PDEs on point cloud data, satisfying PDE constraints and boundary conditions.
NOGaP uses neural operators and GPs to solve PDEs with uncertainty quantification.
problem Lack of uncertainty measures in neural operator solutions for PDEs.
method NOGaP combines neural operators with Gaussian Processes to provide probabilistic solutions.
result NOGaP offers improved prediction accuracy and uncertainty quantification.
Gradients of neural networks can be computed efficiently for any architecture, but some applications require differential operators with higher time complexity. We describe a family of restricted neural network architectures that allow efficient computation of a family of differential operators involving dimension-wise…
Framework learns physics-informed continuum models from molecular data.
problem Discovering accurate and robust data-driven continuum models from molecular simulation data.
method Operator regression framework using neural networks in modal space with physical inductive biases.
result Learned operators generalize to unseen system characteristics.
New method uses neural networks to solve high-dimensional eigenvalue problems.
problem Solving eigenvalue problems in high dimensions.
method Reformulates eigenvalue problem as fixed point problem of semigroup flow, approximated by neural networks.
result Accurate eigenvalue and eigenfunction approximations in various high-dimensional operators.
Guillarmou extends X-ray transform to magnetic and thermostat flows.
problem Stability of magnetic X-ray transforms.
method Generalizes normal operator to thermostat and magnetic flows, proving ellipticity.
result Elliptic pseudodifferential operators of order -1 for generalized normal operators.
Hybrid approach combines VI and HMC for efficient Bayesian inference in neural networks.
problem Computational demands and inaccuracies in Bayesian inference for neural networks.
method Combines VI and HMC, reducing parameter space and accelerating inference.
result Significantly reduces inference time for large neural networks, improving uncertainty quantification.
CMCO provides robust uncertainty estimates for neural operators without retraining.
problem Uncertainty quantification in deep learning for real-time virtual sensing.
method Unified Monte Carlo dropout and split conformal prediction in DeepONet.
result Near-nominal empirical coverage in diverse applications.
New method solves high-dimensional Bayesian inverse problems efficiently.
problem Efficiently solving high-dimensional Bayesian inverse problems with limited data.
method Physics-informed Neural Operators with RealNVP architecture for invertibility and differentiability.
result Accurate approximations of the full posterior without additional forward solves or sampling.
We model how Lipschitz continuity changes during neural network training.
problem Understanding how Lipschitz continuity evolves during training.
method We use a system of stochastic differential equations to capture the dynamics of Lipschitz continuity under SGD.
result We identify three factors driving the evolution of Lipschitz continuity: gradient flow projection, gradient noise, and Hessian projection.
Improved particle-flow event reconstruction for future colliders using scalable neural networks.
problem Efficient and accurate particle reconstruction in future particle detectors.
method Comparative study of scalable machine learning models (graph neural network and kernel-based transformer) for event reconstruction.
result Graph neural network model improves jet transverse momentum resolution by up to 50%.
The article studies curvature operator behavior in 3D under Ricci flow.
problem Understanding curvature operator behavior in 3D under Ricci flow.
method Expressed eigenvalues explicitly and proved curvature operator preservation.
result Curvature operator of the second kind is preserved by Ricci flow in 3D for specific $\a$ values.
PCA-Net combines PCA and neural networks for operator approximation, with new bounds on complexity.
problem Developing approximation theory for PCA-Net architecture.
method Combines PCA and neural networks, derives universal approximation results and lower bounds on complexity.
result PCA-Net can overcome the curse of parametric complexity for specific operators.
New neural operators model turbulence with memory and randomness.
problem Modeling turbulence in complex fluid dynamics with memory and randomness.
method Symmetrized activation functions, fractional derivatives, and stochastic noise.
result Theoretical guarantees for approximation quality in turbulent phenomena.
Study of spectral flow in symmetric Toeplitz operator families.
problem Understanding spectral flow in families of symmetric Toeplitz operators.
method Analog of Atiyah-Singer-Robbin-Salamon theorem for Z2-valued spectral flow. result Graded secondary spectral flow equals secondary index of a Callias-type operator.
Constructs equivariant spectral flow for Dirac-type operators on manifolds.
problem Calculating spectral flow for Dirac-type operators on manifolds with group actions.
method Equivariant spectral flow construction for paths of Dirac-type operators on manifolds.
result Relates delocalised η-invariants and ρ-invariants for different positive scalar curvature metrics.
GC-Flow uses graph flows for better clustering than traditional GCNs.
problem Traditional GCNs miss useful clustering information.
method Designing normalizing flows to replace GCN layers, creating a generative model.
result GC-Flow produces well-separated clusters while maintaining predictive power.
Ancient flows by curvature powers in 2D have finite entropy.
problem Existence of non-homothetic ancient flows by powers of curvature in R2. method Determined Morse indices and kernels of the linearized operator of shrinkers. Constructed flows using unstable eigenfunctions.
result Existence of ancient flows with finite entropy.
Study examines preservation of curvature-adaptedness during mean curvature flow.
problem Preservation of curvature-adaptedness during mean curvature flow.
method Investigates curvature-adaptedness in locally symmetric spaces.
result Curvature-adaptedness is preserved along mean curvature flow.
The spectral flow theorem is applied to operators on finite intervals.
problem Operators on finite intervals without boundary conditions are not Fredholm.
method Interpolation theory is used to define boundary conditions making the operators Fredholm. The spectral flow theorem is applied to find the Fredholm index.
result The Fredholm index is given by the spectral flow of the operator path.
The paper proposes a new method for probabilistic load forecasting using Bernstein-Polynomial Normalizing Flows.
problem High variability in short-term load forecasting at the low-voltage level due to fluctuating demand and increasing electrification.
method Flexible conditional density forecasting based on Bernstein polynomial normalizing flows with neural network control.
result Density predictions outperform traditional methods for 24h-ahead load forecasting.
Hybrid model predicts flow and pressure in water systems.
problem Predicting flow and pressure in water distribution systems with complex spatial-temporal correlations.
method Hybrid dual-stage spatial-temporal attention-based recurrent neural networks (hDS-RNN).
result Our model outperformed 9 baseline models in flow and pressure series prediction.
DeepWeightFlow generates diverse neural network weights efficiently.
problem Generating complete neural network weights efficiently and accurately.
method Flow Matching in weight space with Git Re-Basin and TransFusion.
result DeepWeightFlow generates high-accuracy neural networks without fine-tuning.
Paper studies Laplace operator estimates in harmonic map heat flows.
problem Estimating Laplace operator in harmonic map heat flows outside singularities.
method Investigates estimates using spherical coordinates for T2 and T3 boundary conditions. result Provides higher-order estimates for the Ericksen--Leslie system.
Graph neural networks have become increasingly popular in recent years due to their ability to naturally encode relational input data and their ability to scale to large graphs by operating on a sparse representation of graph adjacency matrices. As we look to scale up these models using custom hardware, a natural assum…
Study fourth-order geometric flow of shape operator for co-dimension one immersions.
problem Analyzing the geometry of isometric immersions in Riemannian manifolds.
method Introduce a moduli flow to decrease curvature variation energy.
result The flow decreases a natural energy measuring curvature variation.
We relate the spectral flow to the index for paths of selfadjoint Breuer-Fredholm operators affiliated to a semifinite von Neumann algebra, generalizing results of Robbin-Salamon and Pushnitski. Then we prove the vanishing of the von Neumann spectral flow for the tangential signature operator of a foliated manifold whe…
Paper proposes hybrid machine learning for tuning first principles models in engineering systems.
problem Inaccurate first principles models in process engineering due to changing conditions.
method Hybrid machine learning framework using Bayesian Neural Networks.
result Uncertainty estimates improve operation decisions in multiphase flow modeling.
A novel spatio-temporal graph neural network with a learnable Tweedie head improves vessel traffic flow prediction in sparse maritime data.
problem Accurate vessel traffic flow prediction in sparse maritime data.
method A model-agnostic learnable Tweedie head attached to ST-GNN backbones.
result The proposed head consistently improves RMSE across multiple ST-GNN backbones, especially on non-zero events.
Study shows splitting schemes can approximate WFR flows faster than the exact flow.
problem Improving sampling efficiency in Wasserstein-Fisher-Rao gradient flows.
method Investigates operator splitting techniques to numerically approximate WFR flows.
result A judicious choice of step size and operator ordering can lead to faster convergence of split schemes to the target distribution.
Horizontal surgery on pseudo-Anosov flows yields almost equivalent flows.
problem Understanding and manipulating pseudo-Anosov flows.
method Performing horizontal surgery on pseudo-Anosov flows by cutting along specific annuli and regluing with a Dehn twist.
result Horizontal Goodman surgery on transitive pseudo-Anosov flows yields an almost equivalent flow.
Study shows trained neural networks can overfit without bias or variance issues.
problem Understanding overfitting in trained two-layer ReLU networks.
method Analysis of gradient flow in the neural tangent kernel regime, decomposition of excess risk.
result Trained networks can overfit benignly without bias or variance issues.
Wave operators and spectral stability for Dirac operators under Ricci flow.
problem Stability of the absolutely continuous spectrum of Dirac operators under Ricci flow.
method Proving existence and completeness of wave operators for Dirac operators and their squares under Ricci flow.
result Criterion for spectral stability of Dirac operators and their squares under Ricci flow without injectivity radius assumptions.
Egorov's theorem for transversally elliptic operators, acting on sections of a vector bundle over a compact foliated manifold, is proved. This theorem relates the quantum evolution of transverse pseudodifferential operators determined by a first order transversally elliptic operator with the (classical) evolution of it…
This work extends GNNs to handle multiple graphs with non-commuting operators, proving transferability.
problem Handling multiple graphs with non-commuting operators in graph neural networks.
method Developed a mathematical theory for graph-tuple neural networks (GtNNs) with non-commuting non-expansive operators.
result Proved universal transferability of GtNNs, ensuring no non-transferable energy under convergence.
This article studies a discrete geometric structure on triangulated manifolds and an associated curvature flow (combinatorial Yamabe flow). The associated evolution of curvature appears to be like a heat equation on graphs, but it can be shown to not satisfy the maximum principle. The notion of a parabolic-like operato…
We consider Ricci flow invariant cones C in the space of curvature operators lying between nonnegative Ricci curvature and nonnegative curvature operator. Assuming some mild control on the scalar curvature of the Ricci flow, we show that if a solution to Ricci flow has its curvature operator which satsisfies R+εI \in C…