Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

79157236314 · May 202619922001200920172026
48 results for dual flow matching

New method improves generative modeling on convex domains using regularized mirror maps and Student-t priors.

problem Challenges in generative modeling on convex domains with heavy-tailed targets.
method Mirror Flow Matching with regularized mirror maps and Student-t priors.
result Empirically outperforms baselines and achieves competitive sample quality.

Study of integral flows on Riemannian manifolds with focus on blow-up profiles and concentration-compactness.

problem Analyzing nonlinear integral flows on Riemannian manifolds with specific focus on blow-up profiles and concentration-compactness.
method Investigation of a family of nonlinear integral flows involving Riesz potentials, focusing on the Hardy-Littlewood-Sobolev (HLS) subcritical and critical regimes.
result Established convergence on unit spheres and certain locally conformally flat manifolds for the dual Yamabe flow.

Symplectic homology matches dual capacities for convex domains.

problem Understanding symplectic capacities and Reeb flows on convex domains.
method Isomorphic filtered symplectic homology to dual singular homology.
result Gutt-Hutchings capacities match spectral invariants for convex domains.

A new method for flow matching reduces computational costs and improves performance.

problem Efficiently matching flow models to target data distributions.
method Semidiscrete formulation of optimal transport (SD-OT) using SGD and maximum inner product search (MIPS).
result Semidiscrete FM (SD-FM) outperforms batch-OT and traditional flow matching methods.

In this paper, we study the dual Anomaly flow, which is a dual version of the Anomaly flow under T-duality. A family of monotone functionals is introduced and used to estimate the dilaton function along the flow. Many examples and reductions of the dual Anomaly flow are worked out in detail.

2019-03-20abs ↗pdf ↗

Study anisotropic inverse Gauss curvature flows and solve dual Orlicz Minkowski problems.

problem Solving dual Orlicz Minkowski problems for anisotropic flows.
method Anisotropic inverse Gauss curvature flows and stationary solutions.
result New existence results for dual Orlicz Minkowski problems for smooth measures.

We present an efficient algorithm for maximum likelihood estimation (MLE) of exponential family models, with a general parametrization of the energy function that includes neural networks. We exploit the primal-dual view of the MLE with a kinetics augmented model to obtain an estimate associated with an adversarial dua…

2019-04-27abs ↗pdf ↗

In this paper the dual Orlicz-Minkowski problem, a generalization of the LpL_p dual Minkowski problem, is studied. By studying a flow involving the Gauss curvature and support function, we obtain a new existence result of solutions to this problem for smooth measures.

2020-01-24abs ↗pdf ↗

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.

Several results on existence and convergence of the Yang-Mills flow in dimension four are given. We show that a singularity modeled on an instanton cannot form within finite time. Given low initial self-dual energy, we then study convergence of the flow at infinite time. If an Uhlenbeck limit is anti-self-dual and has …

2014-02-13abs ↗pdf ↗

Study anisotropic flows without global terms and solve dual Orlicz Christoffel-Minkowski problems.

problem Anisotropic flows without global forcing terms and dual Orlicz Christoffel-Minkowski problems.
method Existence results for dual Orlicz Christoffel-Minkowski type problems via stationary solutions of anisotropic flows.
result Existence results for a class of dual Orlicz Christoffel-Minkowski type problems.

Flow Matching improves statistical guarantees through kernel density estimation.

problem Improving statistical guarantees for generative models.
method Connecting Flow Matching to kernel density estimation and verifying optimal rates of convergence.
result Flow Matching achieves optimal rates up to logarithmic factors for large networks and on lower-dimensional manifolds.

This paper solves the dual Minkowski problem for q-torsional rigidity.

problem The dual Minkowski problem for q-torsional rigidity.
method Introduced the p-th dual q-torsional measure and solved the p-th dual Minkowski problem for q-torsional rigidity using a Gauss curvature flow.
result Existence of smooth even and non-even solutions to the p-th dual Minkowski problem for q-torsional rigidity.

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.

RFM improves CNFs by adding a boundary constraint term and matching velocity fields.

problem Flow matching on constrained domains leads to unnatural samples.
method RFM adds a boundary constraint term and matches velocity fields in a simulation-free manner.
result RFM achieves comparable or better results on standard image benchmarks and produces high-quality samples.

The paper justifies time-dependent loss reweighting schemes for flow matching and diffusion models.

problem Theoretical justification for time-dependent loss reweighting schemes in flow matching and diffusion models.
method Clarifies that the loss can depend on both time and state, and shows theoretical justification for time-dependent loss weighting schemes.
result Time-dependent loss weighting schemes are theoretically justified for Generator Matching and Edit Flows.

This work interprets diffusion score matching using normalizing flows for better model training and evaluations.

problem Limitations of diffusion score matching when dealing with certain types of distributions.
method The approach involves interpreting the diffusion matrix using normalizing flows to provide better interpretation and usage of diffusion score matching.
result Diffusion score matching is equivalent to the original score matching evaluated in the transformed space defined by the normalizing flow.

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.

Paper studies inverse curvature flows and solves related geometric problems.

problem Inverse curvature flows and related geometric problems.
method Analyzes a class of expanding flows with specific speeds and proves existence and convergence.
result Proves the existence and convergence of flows under certain conditions, leading to new solutions to geometric problems.

New error bounds for flow matching methods using deterministic sampling.

problem Improving the accuracy of flow matching methods for generating probability distributions.
method Derived error bounds for flow matching methods under deterministic sampling conditions.
result Presented error bounds for flow matching methods using L2L^2 loss and regularity conditions.

Flow matching adapts to manifold structures without diffusion.

problem Theoretical understanding of flow matching in manifold-supported settings.
method Flow matching with linear interpolation on smooth manifolds, analyzing velocity field and density estimator.
result Non-asymptotic convergence guarantee and statistical consistency of flow matching on manifolds.

Unified framework for continuous-state discrete flow matching models.

problem Discrete generative modeling with continuous probabilities.
method Introducing αα-Flow, a family of CS-DFM models based on information geometry.
result Optimal flow matching loss for αα-flow minimizes generalized kinetic energy.

Generative model for condensed matter using Riemannian flow matching.

problem Sampling equilibrium distributions in condensed-phase systems.
method Riemannian flow matching to incorporate periodicity, using Hutchinson's trace estimator and cumulant expansion for bias correction.
result Highly accurate free energy estimates on monatomic ice without multistage estimators.

Researchers develop Orlov-Schulman symmetries for self-dual conformal structures.

problem Developing symmetries for self-dual conformal structures.
method Explicit proof of compatibility with Lax-Sato flows, dressing scheme based on Riemann-Hilbert problem.
result Construction and proof of compatibility of Orlov-Schulman symmetries.

GLASS Flows improves flow and diffusion model performance by optimizing sampling efficiency.

problem Efficiency bottleneck in sampling Markov transitions for flow and diffusion models.
method Introduces GLASS Flows, a new sampling paradigm that simulates a 'flow matching model within a flow matching model' to sample Markov transitions efficiently.
result Eliminates the trade-off between stochastic evolution and efficiency in large-scale text-to-image models.

The study connects geodesic flows on Riemann surfaces to random walks on their dual graphs.

problem Understanding ergodicity of geodesic flows on infinite Riemann surfaces.
method Analyzing random walks on the dual graph of pants decompositions.
result Equivalence between ergodicity of geodesic flows and recurrence of random walks.