Study shows magnetic trajectories in Berger spheres are homogeneous.
problem Homogeneity of contact magnetic trajectories in Berger spheres.
method Proved every contact magnetic trajectory is a product of a homogeneous geodesic and a charged Reeb flow.
result Contact magnetic trajectories in Berger spheres are homogeneous.
Method identifies coherent structures in sparse flow data.
problem Identifying coherent structures in sparse particle trajectory data.
method Spectral graph theory and hierarchical clustering.
result Algorithm successfully identifies coherent structures in various flows.
A new method detects anomalies in trajectory data using normalizing flows.
problem Detecting anomalous patterns in high-dimensional, varying-length spatial data.
method Probability density estimation via normalizing flows for each trajectory segment, aggregating likelihoods.
result The proposed method, GRADINGS, effectively identifies anomalies in real-world trajectory data.
Method detects trajectory outliers using Hodge Laplacian embeddings.
problem Detecting outliers in trajectory data on simplicial complexes.
method Flow-embeddings using Hodge 1-Laplacian of simplicial complexes.
result Classifies trajectories based on topological behavior.
New flow generates surfaces with constant curvature.
problem Creating surfaces with specific curvature properties.
method Framed curvature flow, analyzing trajectory surfaces.
result Trajectory surfaces of constant mean or Gaussian curvature.
Homogeneous magnetic trajectories in a special linear group proven.
problem Proving homogeneity of magnetic trajectories in a specific group.
method Using contact magnetic curves and geodesics.
result Every contact magnetic trajectory is a product of a homogeneous geodesic and a charged Reeb flow.
Variational inference improves training of generative flow networks.
problem Training generative flow networks efficiently and accurately.
method Define variational objectives in terms of KL divergences and optimize convex combinations.
result Variational inference methods can reduce the variance of gradients in training generative flow networks.
Framework learns continuous dynamics from sparse trajectories.
problem Learning dynamics from sparsely sampled and high-dimensional trajectories.
method Interpolative Multi-Marginal Flow Matching (IMMFM) framework.
result IMMFM outperforms existing methods in forecasting and downstream tasks.
DGFS improves sampling from complex densities by optimizing partial trajectories.
problem Sampling from intractable high-dimensional density functions.
method DGFS uses a flow function to break down the training process into short partial trajectory segments, leveraging intermediate learning signals.
result DGFS achieves more accurate estimates of the normalization constant.
A new method learns straight trajectories in one step for optimal flow matching.
problem Learning flows with straight trajectories for fast inference.
method Optimal Flow Matching (OFM) approach using convex functions for vector fields.
result Recovering straight OT displacements in just one FM step for quadratic transport.
Study counts special paths on complex shapes.
problem Counting special paths on complex shapes.
method Proved a lower bound using gradient flow and homology.
result Lower bound on the number of special paths.
We consider a Morse function f and a Morse-Smale gradient-like vector field X on a compact connected oriented 3-manifold M such that f has only one critical point of index 3. Based on Laudenbach's ideas, we will show that the flow of X can be isotoped into one so that the trajectory spaces of the new flow pro…
In this paper we study the typical speed of a generic earthquake trajectory leaving compact sets in the moduli space of the once-punctured torus. Mirzakhani showed that the earthquake flow is measurably equivalent to the horocyclic flow, which has been studied extensively. Our main result shows that the earthquake flow…
Developed a random walk analog of geodesic flow on hyperbolic groups.
problem Geodesic flow on hyperbolic groups due to non-uniqueness of geodesics.
method Introduced a new framework using random walks and bi-infinite trajectories.
result Established ergodicity of the randomized geodesic flow and exponential mixing.
FLUID uses flows to unify filtering and smoothing for complex systems.
problem Bayesian filtering and smoothing for high-dimensional nonlinear systems.
method FLUID encodes observation histories into a fixed summary statistic, using flows for filtering and smoothing.
result FLUID provides accurate approximations of filtering and smoothing distributions.
JKO-iFlow uses neural ODEs to improve generative models with reduced memory and training complexity.
problem Efficiently training deep generative models in high dimensions with reduced memory and training complexity.
method JKO scheme inspired neural ODE flow network with adaptive time reparameterization.
result JKO-iFlow achieves competitive performance compared to existing models at reduced computational and memory cost.
The paper develops a new theory to understand deep learning optimization.
problem Understanding the dynamics of optimization in deep learning, especially in the edge of stability regime.
method Developed a central flow differential equation to describe the time-averaged trajectory of oscillatory optimizers.
result Central flows can predict long-term optimization trajectories with high numerical accuracy.
Improved GFlowNets learn more efficiently with trajectory balance.
problem Inefficient credit assignment in GFlowNets leads to suboptimal learning.
method Proposed trajectory balance as a new learning objective.
result Trajectory balance leads to more efficient and robust GFlowNet learning.
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.
Gradient flow with weight decay shows grokking effect in deep learning.
problem Understanding the grokking effect in deep learning.
method Analyzing gradient flow dynamics with weight decay.
result Weight decay causes slow norm reduction, explaining grokking.
Study integrability of geodesic flow on specific Lie groups.
problem Integrability of geodesic flow on metabelian nilpotent groups.
method Symplectic reduction procedure applied to sub-Riemannian geodesic flow on metabelian nilpotent groups.
result Showed integrability of normal Hamiltonian flow in Engel-type groups.
Billiard trajectories in curved spaces have predictable travel times.
problem Understanding travel times in billiard trajectories on curved surfaces.
method Analyzing geodesic flows and sectional curvature to prove time-preserving conjugacy.
result Billiard trajectories with almost identical obstacles have identical shapes.
Efficiently trains forward processes to minimize generative trajectories curvature.
problem High curvature of generative trajectories slows down sampling speed.
method Trains forward process to minimize curvature without ODE/SDE simulation.
result Lower curvature than previous models, decreased sampling costs.
Discrete Flow Maps bypass sequential prediction limits for parallel text generation.
problem Sequential autoregressive prediction limits large language model speed.
method Flow Maps compress generative trajectories into single-step mappings.
result Discrete Flow Maps surpass previous state-of-the-art results in discrete flow modeling.
Hamilton flows on Kähler manifold for which all trajectories are H-planar curves (complex analog of geodesics) are considered. These flows are called H-planar. The equation which has to obey the Hamiltonian of H-planar Hamilton flow is received and the method of finding general solution of this equation is propos…
Paper establishes a generalization bound for gradient flow using a data-dependent kernel.
problem Understanding the generalization properties of gradient-based optimization methods.
method Establishes a generalization bound for gradient flow through a data-dependent kernel called the loss path kernel (LPK).
result The LPK captures the entire training trajectory and leads to tighter generalization guarantees.
A magnetic field is defined by the property that its divergence is zero in a three dimensional oriented Riemannian manifold. Each magnetic field generates a magnetic flow whose trajectories are curves called as magnetic curves. In this paper, we give a new variational approach to studies the magnetic flow asociated wit…
New model explains why metaorder impact estimation is hard with public data.
problem Difficulty in estimating metaorder impact using public market data.
method Proposed a modified Transient Impact Model to better describe order flow.
result Model shows market impact can be permanent under certain conditions.
Study of intersections in Hamiltonian orbits on cotangent bundles.
problem Understanding intersections of projected Hamiltonian orbits in cotangent bundles.
method Generic submersive level set analysis, multi-jet transversality theorem.
result Projected Hamiltonian orbits have discrete intersections, which can be perturbed away under certain conditions.
Given a closed Riemannian manifold of dimension n and a Morse-Smale function, there are finitely many n-part broken trajectories of the negative gradient flow. We show that if the manifold admits a hyperbolic metric, then the number of n-part broken trajectories is always at least the hyperbolic volume. The proof…
A framework learns multiscale dynamics from single trajectories using normalizing flows.
problem Learning effective stochastic dynamics from single observed paths of slow variables.
method Data-driven approach based on coupled multiscale SDEs, stochastic averaging, and normalizing flows for density modeling.
result Scalable approach to capturing epistemic uncertainty in multiscale systems.
TFM trains Neural SDEs without backpropagation, improving clinical time series modeling.
problem Modeling irregularly sampled time series in medicine.
method Trajectory Flow Matching (TFM) using flow matching for generative modeling.
result TFM improves performance on clinical time series datasets.
New analysis shows FM learns underlying dynamical structure, not just trajectory replay.
problem Understanding whether flow matching models learn transferable dynamical structure or merely replay trajectories.
method Derived velocity field implied by FM objective, characterized as a continuous-time dynamical system.
result FM models can be seen as parametric surrogates of nonparametric solutions, providing strong probabilistic forecasts.
With a view to constructing a Morse/Floer homology theory for CMC hypersurfaces, we prove a compactness result modulo broken trajectories for eternal mean curvature flows with forcing term in compact, hyperbolic manifolds.
A new method uses coherent structure coloring to estimate model parameters more accurately than traditional methods.
problem Challenges in estimating model parameters from Lagrangian data in turbulent flows.
method Use coherent structure coloring (CSC) field to assess model skill and estimate model parameters.
result Error in the CSC field can accurately determine model parameters, while conventional methods fail.
Generative models need per-sample confidence scores to improve quality and stability.
problem Generative models produce unreliable outputs and lack confidence measures.
method Flow Matching with Confidence (FMwC) injects noise and integrates it through the network, providing per-sample confidence scores.
result The confidence score correlates with the velocity field's divergence, offering insights into generative processes.
Paper proves higher-order flow matching preserves optimality in generative modeling.
problem Theoretical guarantees for higher-order flow matching in generative modeling.
method Neural network approximations with controlled depth, width, and sparsity.
result Proves worst case optimality for second-order flow matching.
Minimal hypersurfaces can't always be connected by mean curvature flow.
problem Existence of connecting mean curvature flows for minimal hypersurfaces.
method Minimal hypersurface analogue of gradient flow trajectories between critical points.
result Additional topological and variational obstructions to connecting mean curvature flows.
Graph Neural Networks model 3D granular flow simulations.
problem Accurate modeling of complex 3D granular flow processes.
method Graph Neural Networks approach to simulate 3D granular flow using LIGGGHTS.
result Machine learning trajectories match physical granular flow processes.
We notice that a generic nonsingular gradient field v=∇f on a compact 3-fold X with boundary canonically generates a simple spine K(f,v) of X. We study the transformations of K(f,v) that are induced by deformations of the data (f,v). We link the Matveev complexity c(X) of X with counting the …
Final version. To appear in Discrete and Continuous Dynamical Systems - A.
We accelerate CNF by reducing ODE truncation errors with polynomial regularization.
problem High computation cost of CNF due to large truncation errors in solving ODEs.
method Add polynomial regularization to approximate ODE trajectories with polynomial functions.
result 42.3% to 71.3% reduction of NFE on density estimation, 19.3% to 32.1% on variational auto-encoder.
Recently, clustering moving object trajectories kept gaining interest from both the data mining and machine learning communities. This problem, however, was studied mainly and extensively in the setting where moving objects can move freely on the euclidean space. In this paper, we study the problem of clustering trajec…
We use the heat flow on the loop space of a closed Riemannian manifold to construct an algebraic chain complex. The chain groups are generated by perturbed closed geodesics. The boundary operator is defined in the spirit of Floer theory by counting, modulo time shift, heat flow trajectories that converge asymptotically…
Gradient flow of elastic energy converges to elastica.
problem Optimizing closed curves to minimize elastic energy.
method Proving the existence of a unique global solution and convergence via Łojasiewicz--Simon gradient inequality.
result Convergence to elastica established for the H2(ds)-gradient flow of modified elastic energy. We present a frame-invariant method for detecting coherent structures from Lagrangian flow trajectories that can be sparse in number, as is the case in many fluid mechanics applications of practical interest. The method, based on principles used in graph coloring and spectral graph drawing algorithms, examines a measur…
Model predicts traffic flow dynamics from sparse data.
problem Predict traffic flow from limited data.
method Mesoscopic model using factor graphs and message passing.
result Efficiently estimates traffic conditions with low probe vehicle penetration.
We prove a spectral flow formula for one-parameter families of Hamiltonian systems under homoclinic boundary conditions, which relates the spectral flow to the relative Maslov index of a pair of curves of Lagrangians induced by the stable and unstable subspaces, respectively. Finally, we deduce sufficient conditions fo…