sFML learns stochastic dynamical systems from data.
problem Learning unknown stochastic dynamical systems from measurement data.
method sFML extends FML for deterministic systems, using a stochastic flow map composed of deterministic and stochastic sub-maps.
result sFML constructs a stochastic evolution model approximating unknown stochastic systems.
Riemannian stochastic gradient descent approximates a diffusion process called Riemannian stochastic modified flow.
problem Improving convergence rate of Riemannian stochastic gradient descent.
method Using stochastic differential geometry, the paper shows RSGD can be approximated by the Riemannian stochastic modified flow (RSMF).
result RSGD can be approximated by the solution to the RSMF driven by an infinite-dimensional Wiener process, increasing the order of approximation.
We show that stochastic interpolation flow maps are Lipschitz with a sharp constant.
problem High dimensional sampling and transport problems.
method Investigating stochastic interpolation flow for generating data samples.
result Stochastic interpolation flow maps are Lipschitz with a sharp constant matching optimal transport maps.
We first prove stochastic representation formulae for space-time harmonic mappings defined on manifolds with evolving Riemannian metric. We then apply these formulae to derive Liouville type theorems under appropriate curvature conditions. Space-time harmonic mappings which are defined globally in time correspond to an…
Itô maps provide a method for any-step SDE integration.
problem Stochastic dynamics
method Itô map formulation
result Empirical results on synthetic and image-generation benchmarks
We convert deterministic flow models to stochastic samplers.
problem Deterministic flow models are sensitive to errors and cannot condition on intermediate states.
method Transform ODEs into SDEs with the same marginal distributions.
result Empirically outperforms deterministic samplers and controls generation diversity.
CoSMIC extends flow-based SVI to transdimensional problems.
problem Bayesian structure learning and model selection with multi-model parameter spaces.
method Normalizing flows with a combined stochastic variational transdimensional inference approach.
result Improved performance on high-cardinality model spaces.
MFMs enable efficient reward alignment for generative models.
problem Computational bottleneck in controlling generative models.
method Meta Flow Maps (MFMs) extend consistency models and flow maps to stochastic regime for efficient value function estimation.
result MFMs enable inference-time steering and unbiased, off-policy fine-tuning to general rewards efficiently.
The study characterizes straight-line flows in dynamic measure transport.
problem Tackles the challenge of designing flows that are easy to integrate.
method Characterizes straight-line flows using a PDE and Reynolds tensor.
result Characterizes affine-in-time interpolants and necessary conditions for flow geometry.
SCALLOP improves likelihood flow maps for efficient Boltzmann generation.
problem Efficient estimation of model likelihood in flow-based generative models.
method SCALLOP introduces a Hutchinson-free likelihood distillation objective for scalable flow-based models.
result SCALLOP achieves up to 10x inference speedup while improving performance.
Mathematical analysis of SNE and t-SNE for dimension reduction.
problem Optimal mapping of high-dimensional data to low dimensions.
method Gradient flow of relative entropy to minimize the distance between points.
result The diameter of the evolving sets remains bounded for SNE but may blow up for t-SNE.
Study on straight-line flows for generative modeling with theoretical obstructions.
problem Existence and obstructions of straight-line flows in generative modeling.
method Characterizations of straight-line flows through PDEs involving conditional statistics of stochastic processes.
result Sharp dichotomy in the existence of straight-line flows for targets with well-separated modes.
The paper proposes a method to learn evolving multivariate distributions from sample paths.
problem Learning the temporal evolution of multivariate densities from sample data.
method Normalizing flows to construct time-dependent mappings.
result The method can approximate evolving probability density functions from observed data.
A scalable algorithm for sampling and fine-tuning models using Tilt Matching.
problem Efficient sampling and fine-tuning of generative models.
method Tilt Matching, arising from a dynamical equation, minimizes variance and inherits regularity from stochastic interpolants.
result Empirically verified to be efficient and highly scalable, providing state-of-the-art results.
Stochastic flows of Stratonovich stochastic differential equations on exotic spheres have been studied. The consequences of the choice of exotic differential structure on stochastic processes taking place on the topological space Sm+n+1 as state space of the processes have been investigated. More precisely, we hav…
Recent advances in variational inference enable the modelling of highly structured joint distributions, but are limited in their capacity to scale to the high-dimensional setting of stochastic neural networks. This limitation motivates a need for scalable parameterizations of the noise generation process, in a manner t…
Unified framework maps financial market dynamics using TE and KM, revealing directional information flow.
problem Challenges in traditional correlation analysis of financial markets, especially during crises.
method Combines Transfer Entropy (TE) and Kramers-Moyal (KM) expansion to analyze dynamic interactions among major indices.
result Increased directional information flow during crises, highlighting gold-dollar and oil-equity linkages.
A new method for normalizing flows using stochastic interpolants simplifies likelihood estimation and improves efficiency.
problem Efficient and scalable likelihood estimation for complex probability distributions.
method Inference of velocity field from time-dependent density interpolating between base and target densities.
result Simplified quadratic loss for velocity estimation, leading to faster and more efficient training.
Geometry arising from two diffusion operators (smooth semi-elliptic, second order differential operators) on different spaces but intertwined by a smooth map is described. Particular cases arise from Riemannian submersions when the operators are Laplace-Beltrami operators, from equivariant operators on the total space …
Covariance shrinkage via stochastic interpolation
problem High-dimensional covariance estimation
method Recasting shrinkage as empirical risk minimization
result Reduces statistical risk through scheduling, flow maps, and early stopping
Develops a framework to analyze financial structures.
problem Difficulty in systematic analysis, comparison, and verification of financial structures.
method Formalizes financial structures as structured allocation systems with explicit allocation operators.
result Specifies inputs, structural requirements, and feasibility restrictions for financial structures.
In this paper, we investigate the Gauss maps of a Ricci-mean curvature flow. A Ricci-mean curvature flow is a coupled equation of a mean curvature flow and a Ricci flow on the ambient manifold. Ruh and Vilms proved that the Gauss map of a minimal submanifold in a Euclidean space is a harmonic map, and Wang extended thi…
Normalizing flows are a powerful class of generative models for continuous random variables, showing both strong model flexibility and the potential for non-autoregressive generation. These benefits are also desired when modeling discrete random variables such as text, but directly applying normalizing flows to discret…
Paper studies heat flow for maps on manifolds, avoiding singularities.
problem Avoiding singularities in heat flow for maps on manifolds.
method Introduces regularized conformal heat flow for n-harmonic maps. result Regularized n-conformal heat flow does not develop finite time singularities. New rigidity estimate derived via harmonic map flow.
problem Rigidity of maps from S2 to S2. method Harmonic map flow approach.
result Rigidity estimate derived.
Study on stochastic mean curvature flow on networks using Ito calculus.
problem Understanding the dynamics of network structures under random influences.
method Application of Ito calculus to derive a stochastic differential equation (SDE) for network edges.
result New insights into the stability, long-term behavior, and pattern formation of complex networks under stochastic influences.
Constructs a moment map flow for isotropic maps on surfaces.
problem Understanding isotropic maps on surfaces and their properties.
method Develops a Kähler moment map geometry and a modified moment map flow.
result Polyhedral modified moment map flow induces a strong deformation retraction.
Study sesqui-harmonic map flow from Riemannian surfaces
problem Investigate sesqui-harmonic map flow from Riemannian surfaces
method L2-gradient flow of an energy functional
result Generalizes Struwe's regularity result for harmonic maps
This work introduces a new method for coupling base and target densities in generative models.
problem Generating samples from complex target distributions using simple base distributions.
method Developed a framework of stochastic interpolants with data-dependent couplings.
result Constructing dynamical transport maps that serve as conditional generative models.
Stochastic normalizing flows use SDEs for efficient training and sampling.
problem Efficient maximum likelihood estimation and variational inference.
method Continuous normalizing flows extended with stochastic differential equations (SDEs) and rough path theory.
result Stochastic normalizing flows enable efficient training and sampling from complex distributions.
The Liouville theorem is proven for V T-harmonic map heat flow.
problem Proving Liouville theorems for V T-harmonic maps.
method Analyzing heat flow on manifolds with specific properties.
result Liouville theorems established for V T-harmonic maps.
Study heat flow for half-harmonic maps and harmonic maps with free boundary.
problem Integrability and regularity of half-harmonic maps and harmonic maps with free boundary.
method Introduced a heat flow associated to half-harmonic maps and constructed weak solutions via Ginzburg-Landau approximation.
result Proved partial regularity of weak solutions in space and time.
Harmonic map flow preserves almost-holomorphic maps without singularities.
problem Preserving almost-holomorphic maps without singularities.
method Harmonic map flow applied to almost-holomorphic maps.
result No singularities or necks appear in the limit at singular times.
Study proves existence of non-trivial harmonic map flows to hemispheres.
problem Existence of non-trivial harmonic map flows to hemispheres.
method Construction of infinitely many weak solutions to harmonic map flow starting from non-minimizing but stationary maps.
result Proves existence of non-trivial self-expanding harmonic map flows to hemispheres.
New algorithm classifies and generates genomic sequences using RG-flow categorifier.
problem Classifying and generating genomic sequences for disease prediction.
method RG-flow based categorifier combining quantum field theory, holographic duality, and neural ODEs.
result RG categorifier can classify and generate new sequences from genomic data.
Maximum entropy modeling is a flexible and popular framework for formulating statistical models given partial knowledge. In this paper, rather than the traditional method of optimizing over the continuous density directly, we learn a smooth and invertible transformation that maps a simple distribution to the desired ma…
Study on test risk dynamics in learning theory with stochastic gradient flow.
problem Understanding test risk in stochastic gradient flow dynamics.
method Path integral formulation for small learning rates, explicit computation for weak features.
result Explicit corrections due to stochastic term in dynamics, good agreement with simulations.
A new method improves generative models by learning lower-dimensional representations.
problem Normalizing flows cannot learn lower-dimensional representations of data.
method Noisy injective flows (NIF) that map latent space to a learnable manifold in high-dimensional data space using injective transformations and an additive noise model.
result Simple application of NIF to existing flow architectures significantly improves sample quality and yields separable data embeddings.
SurVAE Flows combine VAEs and flows using surjective transformations.
problem Combining the strengths of VAEs and flows to model complex densities.
method Modular framework of composable deterministic and stochastic transformations.
result Exact likelihood computation and lower bound on likelihood.
Quantum stochastic flow computes heat kernel traces for Ricci flat manifolds.
problem Computing heat kernel traces for Ricci flat manifolds.
method Quantum stochastic differential equation (qsde) on Fock space over L2 differential 1-forms, adapted flow construction. result Trace of the connection Laplacian heat kernel can be computed over any compact Ricci-flat Riemannian manifold.
Cryo-EM reconstruction is reformulated as a stochastic inverse problem to handle structural heterogeneity.
problem Handling structural heterogeneity in cryo-EM 3D reconstruction.
method Formulated as a stochastic inverse problem over probability measures, using variational discrepancy and Wasserstein gradient flow.
result Validated approach using synthetic examples, demonstrating recovery of continuous structural distributions.
Study proves short-term existence for harmonic maps under evolving metrics.
problem Analyzing harmonic maps under time-dependent metrics.
method Proves short-term existence for harmonic map heat flow coupled with a smooth family of complete metrics.
result Generalizes short-term existence results for harmonic map heat flow.
Study on biharmonic map heat flow with monotonicity formula.
problem Properties of biharmonic heat kernel and extrinsic biharmonic map heat flow.
method Derived an entropy type quantity exhibiting monotonicity behaviors.
result Monotonicity formula for extrinsic biharmonic map heat flow.
Strict type-II blowup in harmonic map flow is proven to have Hölder continuous body map.
problem Finite-time singularity of harmonic map flow.
method Analysis of outer energy scale and Hölder continuity proof.
result Strictly type-II blowup body map is Hölder continuous.
In this paper we study the Teichmüller harmonic map flow as introduced by Rupflin and Topping [15]. It evolves pairs of maps and metrics (u,g) into branched minimal immersions, or equivalently into weakly conformal harmonic maps, where u maps from a fixed closed surface M with metric g to a general target manif…
Bayesian method finds voids in galaxy surveys with deep neural networks.
problem Finding genuine matter underdensities in sparse galaxy surveys is underconstrained.
method Deep graph neural network evolves 'test particles' to sample from stochastic void definitions.
result Trained model performs well and finds Bayes-optimal void mappings.
Closed-form flow matching yields similar performance to stochastic version, improving model performance.
problem Understanding why flow matching models generalize well.
method Empirical analysis and comparison of stochastic and closed-form flow matching losses.
result Closed-form flow matching can improve model performance.
Global existence and convergence of heat flow for p-harmonic maps.
problem Global existence and convergence of heat flow for p-harmonic maps between manifolds.
method Analysis of heat flow equations for p-harmonic maps.
result Global existence and convergence of heat flow for p-harmonic maps under certain conditions.