Flow Matching enables robust training of CNFs with various probability paths.
problem Training Continuous Normalizing Flows (CNFs) at large scales.
method Flow Matching (FM) is a simulation-free approach for training CNFs by regressing vector fields of conditional probability paths.
result Flow Matching with diffusion paths yields more robust and stable training compared to diffusion-based methods.
Generalizes Bochner formula to path space for Ricci flow.
problem Characterize solutions of the Ricci flow.
method Generalizes Bochner formula to parabolic path space.
result Characterizations of the Ricci flow from Bochner inequalities.
Improved sampling efficiency for molecular systems using path gradients after Flow Matching.
problem Improving sampling efficiency for complex molecular systems.
method Hybrid approach combining Flow Matching and path gradients.
result Up to a threefold increase in sampling efficiency for molecular systems.
New path-gradient estimator for continuous normalizing flows.
problem Limitation of simple Gaussian variational distributions in complex applications.
method Proposed a path-gradient estimator for continuous normalizing flows.
result Empirical evidence of superior performance of the new estimator.
Generative Flow Networks solve shortest path problems in graphs.
problem Finding shortest paths in graphs.
method Generative Flow Networks with flow regularization.
result Training a GFlowNet can solve pathfinding problems in arbitrary graphs.
New probability path model improves flow matching forecasting performance.
problem Impact of probability path model selection on flow matching forecasting performance.
method Proposed a novel probability path model designed to improve forecasting performance.
result Our model achieves faster convergence during training and improved predictive performance compared to existing models.
Improved KL divergence estimators for normalizing flows lead to faster convergence and better approximations.
problem Estimating KL divergences for normalizing flows efficiently and accurately.
method Path-gradient estimators for reverse and forward KL divergences.
result Path-gradient estimators lead to faster convergence and better approximation results.
Adversarial reinforcement learning optimizes microswimmers' path-planning in turbulent flows.
problem Optimizing microswimmers' paths in turbulent flows for efficient target reach.
method Adversarial-reinforcement learning scheme applied to 2D and 3D turbulent flows.
result Microswimmers can reach targets faster than a naive approach in turbulent flows.
A new path gradient estimator speeds up normalizing flows without sacrificing accuracy.
problem High computational cost and limited scalability of path gradient estimators for normalizing flows.
method Proposed a fast path gradient estimator that improves computational efficiency and scalability.
result The new estimator achieves superior performance and reduced variance across various applications.
We consider a continuous path of bounded symmetric Fredholm bilinear forms with arbitrary endpoints on a real Hilbert space, and we prove a formula that gives the spectral flow of the path in terms of the spectral flow of the restriction to a finite codimensional closed subspace. We also discuss the case of restriction…
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.
Extends RSP model with net flow and capacity constraints for better network analysis.
problem Improving shortest path models with net flows and capacity constraints.
method Developed net flow RSP model and introduced capacity constraints. Proposed algorithms for computing expected routing costs and solving constrained problems using Lagrangian duality.
result Net flow RSP dissimilarity measure is competitive with state-of-the-art dissimilarities.
Proves path-connectedness of 2-convex embedded spheres moduli space.
problem Path-connectedness of moduli space of 2-convex embedded spheres.
method Mean curvature flow with surgery.
result Proves path-connectedness for every n.
Researchers compare different gradient methods for ridge regression, finding conjugate gradients have similar performance.
problem Comparing statistical properties of different gradient methods in ridge regression.
method Explicit non-standard error decomposition to bound prediction error of conjugate gradient iterates.
result Conjugate gradient iterates share optimality properties with gradient flow and ridge regression up to a constant factor.
A formula is given in terms of secondary characteristic classes for the leading order contribution to the spectral flow for a path of twisted Dirac operators on an odd dimensional, Riemannian manifold when the twisting is done by a path of unitary connections with large curvature.
New method reduces discrete flow transitions, improving perplexity estimation.
problem Stochasticity in discrete paths makes rectification strategies ineffective.
method Dynamic-optimal-transport-like minimization objective with minibatch strategies.
result 32 times reduction in transitions for same perplexity.
Path regularization improves GFlowNets exploration and generalization.
problem Improving GFlowNets exploration and generalization.
method Path regularization based on optimal transport theory.
result Path regularization enhances GFlowNets to generate more diverse and novel candidates.
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…
Proves path-connectedness of metrics on 3-manifolds with positive scalar curvature.
problem Proving path-connectedness of metrics on 3-manifolds with positive scalar curvature.
method Uses Ricci flow with surgery and infinite connected sums with geometry control.
result Proves the moduli space of metrics is path-connected.
BWFlow improves graph generation by smoothly interpolating graph components.
problem Disjoint modeling of graph nodes and edges leads to irregular and non-smooth probability paths.
method Modeling graphs as MRFs and using optimal transport displacement for a smooth probability path.
result BWFlow achieves better training convergence and efficient sampling in graph generation.
Bounds on gradient descent and flow paths for convex and nonconvex functions.
problem Understanding the path length of gradient descent and flow curves.
method Analytical derivation of path length bounds for various smooth convex and nonconvex functions.
result Bounds on path length ζ for gradient descent and flow, providing insights into convergence properties. Improved flow matching using Gaussian processes for better sample quality.
problem Training continuous normalizing flows with reduced variance and flexibility.
method Extending conditional flow matching to streams modeled with Gaussian processes.
result Improved quality of generated samples with moderate computational cost.
The author has previously constructed a class of admissible vector fields on the path space of an elliptic diffusion process x taking values in a closed compact manifold. In this Note the existence of flows for this class of vector fields is established and it is shown that the law of x is quasi-invariant under the…
The study examines mean curvature flow and Heegaard surfaces in lens spaces.
problem Analyzing mean convex two-spheres and Heegaard tori in lens spaces.
method Proves path-connectedness of moduli spaces of mean convex two-spheres and Heegaard tori in manifolds with nonnegative Ricci curvature.
result There are always either one or two path components of mean convex Heegaard tori in lens spaces, depending on the ambient manifold's homotopy type.
CNFs learn on manifolds using PPD, improving likelihood and sample quality.
problem Training CNFs on manifolds efficiently and accurately.
method Minimizing PPD, a novel divergence, to train CNFs on manifolds.
result CNFs trained with PPD achieve state-of-the-art results on manifold benchmarks.
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.
Study uses Bayes Hilbert framework to recover probability measure flows from sensors.
problem Recovering probability measure flows from moving sensors in a Hilbert space.
method Bayes Hilbert framework, minimum-energy transport, linearization, variational theory.
result Localized sensors can recover reduced path directions but not full state space.
Smooth flow of a complex curve proven.
problem Proving smoothness of level-set flow for complex curves.
method Analyzing the topologist's sine curve and its evolution under level-set flow.
result First example of a non-locally-connected set evolving smoothly.
New index for evaluating cash flow processes over a fixed horizon.
problem Evaluating performance of cash flow processes over a fixed investment horizon.
method Extended acceptability indices to càdlàg processes, providing a new index based on Average Value-at-Risk and running minimum.
result Suggested index represents a RAROC-type model for performance evaluation.
FFM generates functions between Gaussian and data distributions.
problem Generating functions between Gaussian and data distributions.
method Define a path of measures, learn a vector field to generate this path.
result FFM outperforms other function-space generative models.
This study examines biases in flow matching samplers using finite-sample estimation.
problem Biases in flow matching samplers when using finite-sample surrogates.
method Finite-sample plug-in estimation and hierarchy of empirical FM models.
result Exact empirical minimizer and smoothed plug-in regime identified for affine conditional flows.
Adapts flow matching for MCMC to improve sampling efficiency.
problem Improving sampling efficiency in MCMC for complex distributions.
method Combines Markov chain and CNFs to learn a path between distributions.
result Achieves similar performance to state-of-the-art methods but with lower computational cost.
FlowGN tackles graph representation learning by tracing information flow paths.
problem GCNs struggle with over-smoothing and scalability issues.
method FlowGN introduces a 'SourceoSink' mode and 'information flow path' concept. result FlowGN outperforms state-of-the-art GCNs in public datasets.
New algorithmic view of ℓ2 regularization using ODEs and path-following methods.
problem Optimizing convex loss functions with ℓ2 regularization.
method Established an equivalence between ℓ2-regularized solution paths and ODEs, proposing path-following algorithms based on homotopy methods and numerical ODE solvers.
result The solution path can be viewed as a hybrid of gradient descent and Newton method, providing novel schemes to choose grid points and reducing computational cost.
New graph distances derived from optimal transport framework using path flows.
problem Develop new graph distances for clustering and classification.
method Bag-of-paths framework with Gibbs-Boltzmann distribution and optimal transport relaxation.
result Interpolates between shortest-path and resistance distances, improving performance.
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.
TrajectoryNet models dynamic cellular trajectories using optimal transport.
problem Modeling continuous and non-linear paths in dynamic processes.
method Continuous normalizing flows linked to dynamic optimal transport.
result TrajectoryNet improves interpolation of cellular distributions.
Develops a new calculus for stochastic processes with occupation flows.
problem Analyzing the behavior of stochastic processes with occupation flows.
method Itô calculus for occupied processes, Feynman-Kac approach.
result Unified Markovian lifts for pricing financial derivatives.
New algorithm computes Schrödinger Bridge for unpaired data translation.
problem Computing optimal transport maps for unpaired data translation.
method Schrödinger Bridge Flow, a discretization of a flow of path measures.
result Eliminates the need to train multiple DDM-like models.
Refines discrete Morse theory to reconstruct homotopy type of CW complexes.
problem Recover homotopy type of CW complexes from partial matchings.
method Introduces flow paths with partial order to reconstruct homotopy type.
result Classifying space of constructed 2-category is homotopy equivalent to CW complex.
In this paper we prove that the moduli space of metrics with positive scalar curvature of an orientable compact 3-manifold is path-connected. The proof uses the Ricci flow with surgery, the conformal method, and the connected sum construction of Gromov and Lawson. The work of Perelman on Hamilton's Ricci flow is fundam…
Synthetic tabular data synthesis models balance utility and risk.
problem Generating synthetic tabular data for regulated domains.
method Latent flow models with various learning targets, paths, and sampling methods.
result Velocity and posterior matching objectives yield higher utility, while score and noise matching achieve lower risk.
Simplified GAN training via gradient flows in kernel space.
problem Training particle transport from source to target distribution.
method Sobolev descent, following gradient flows in kernel space or neural networks.
result Convergence to target distribution in MMD sense with regularization.
Proves CLT for Brownian paths on pinched negative curvature manifolds.
problem Distribution of Brownian paths on pinched negative curvature manifolds.
method Proof of central limit theorem for distances and Green functions.
result Central limit theorem holds for Brownian paths in pinched negative curvature.
We establish a splitting formula for the spectral flow of the odd signature operator on a closed 3-manifold M coupled to a path of SU(2) connections, provided M = S cup X, where S is the solid torus. It describes the spectral flow on M in terms of the spectral flow on S, the spectral flow on X (with certain Atiyah-Pato…
This paper bridges variational inference and Wasserstein gradient flows.
problem Combining variational inference and Wasserstein gradient flows for more efficient approximations.
method Recasting Bures-Wasserstein gradient flow as a Euclidean gradient flow and using path-derivative gradient estimator.
result A new gradient estimator for f-divergences that can be implemented using machine learning libraries. New method for estimating diffusion model densities without solving flows.
problem Estimating log densities from diffusion models efficiently.
method Monte Carlo path integral estimation, avoiding flow solving.
result Significantly more scalable and efficient density estimation.
The study finds infinitely many periodic orbits that can be used to modify Anosov flows.
problem Can surgeries on periodic orbits of Anosov flows produce equivalent flows?
method Analyzing suspension Anosov flows, the study identifies pairs of periodic orbits that can be used to modify the flow.
result For some suspension Anosov flows, there exist infinitely many pairs of periodic orbits that can be used to modify the flow.