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.

168,742 papers · 148 categories

Trend · papers per month

4.2%8.3%12.5%16.7% · Sep 199519922001200920172026
48 results for continuous-time flows

CT-OT Flow estimates continuous-time dynamics from discrete snapshots.

problem Estimating continuous-time dynamics from temporally aggregated snapshots with noisy or uncertain timestamps.
method Two-stage framework: aligning neighboring intervals via partial optimal transport (POT) and reconstructing a continuous-time distribution through temporal kernel smoothing.
result Reduces distributional and trajectory errors compared with existing methods across synthetic and real datasets.

Continuous-time Kyle model shows privacy subsidy from noise-perturbed order flow.

problem Quantifying break-even fees for committed-AMM exchanges under privacy-aggregated information.
method Extended Nakamura's (2026) single-period result to continuous-time, observing order flow perturbed by Brownian noise.
result Cumulative privacy subsidy is identified as equivalent to Loss-Versus-Rebalancing in price observation gap.

Deep learning networks are approximated using dynamical systems theory.

problem Understanding the approximation capabilities of deep learning networks.
method Modeling deep residual networks as continuous-time dynamical systems and using approximation theories in LpL^p.
result Established general sufficient conditions for universal approximation of deep residual networks.

Two fundamental problems in unsupervised learning are efficient inference for latent-variable models and robust density estimation based on large amounts of unlabeled data. Algorithms for the two tasks, such as normalizing flows and generative adversarial networks (GANs), are often developed independently. In this pape…

2017-09-04abs ↗pdf ↗

A new algorithm for minimizing functions on Wasserstein space.

problem Discretization of continuous Wasserstein gradient flows in machine learning.
method Forward-Backward discretization scheme for minimizing functions with smooth and nonsmooth components.
result The FB scheme converges similarly to proximal gradient algorithms in Euclidean spaces.

Proposes a continuous flow model to understand and control instability in gradient descent for deep learning.

problem Understanding and controlling the instability of gradient descent in deep learning.
method Introduces the Principal Flow (PF), a continuous time flow that approximates gradient descent dynamics.
result The PF captures divergent and oscillatory behaviors of gradient descent, including escaping local minima and saddle points.

Investigates gradient descent dynamics and introduces new regularisation methods.

problem Understanding and mitigating gradient descent instabilities and interactions with smoothness regularisation.
method Derives continuous-time flows to account for discretisation drift, constructs learning rate schedules and regularisers.
result New regularisation methods improve performance in reinforcement learning.

Study on markets with insiders receiving private signals affecting asset prices and information flow.

problem Understanding markets with heterogeneous information flows and private signals.
method Proves existence of a partial communication equilibrium with jumps in information and prices.
result The public information flow and asset prices jump at each private signal time, creating incomplete markets between jumps.

Geometric tempering improves sampling from distributions, with exponential convergence rates.

problem Sampling from probability distributions using gradient flow dynamics.
method Geometric tempering of the target distribution in Wasserstein and Fisher-Rao gradient flows.
result Exponential convergence in continuous and discrete time for geometric tempering.

We study the statistical properties of the iterates generated by gradient descent, applied to the fundamental problem of least squares regression. We take a continuous-time view, i.e., consider infinitesimal step sizes in gradient descent, in which case the iterates form a trajectory called gradient flow. Our primary f…

2018-10-23abs ↗pdf ↗

We establish a foundation for multivariate counterfactual identification using dynamic optimal transport.

problem Addressing the open question of counterfactual identification for high-dimensional multivariate outcomes from observational data.
method Establish a foundation for multivariate counterfactual identification using continuous-time flows, including non-Markovian settings, with tools from dynamic optimal transport.
result Characterise the conditions under which flow matching yields a unique, monotone, and rank-preserving counterfactual transport map, ensuring consistent inference.

Novel approach finds implicit regularisation in two-player games using BEA.

problem Understanding implicit regularisation in two-player games.
method Using backward error analysis to construct continuous-time flows with gradient-eligible vector fields.
result Identifies new implicit regularisation effects in two-player games.

A new framework solves complex optimization problems with continuous worst-case distributions.

problem Optimizing under uncertain distributions with continuous worst-case scenarios.
method Flow-based distributionally robust optimization (DRO) with Wasserstein uncertainty sets and invertible transport maps.
result The framework finds continuous worst-case distributions and samples efficiently.

Flow-SSN improves segmentation efficiency and accuracy.

problem Challenges in medical imaging segmentation, especially high-rank pixel-wise covariances.
method Generative segmentation model using discrete-time autoregressive and continuous-time flow variants.
result Flow-SSNs can estimate high-rank pixel-wise covariances efficiently without assuming rank or storing parameters.

New entropy flow method extends generalization bounds for all Markov algorithms.

problem Understanding generalization error for Markov algorithms.
method Unified framework using continuous-time approximation and modified logarithmic Sobolev inequalities.
result Established new connections between generalization error and ergodic properties of Markov processes.

TriTPP models enable faster and more flexible event data modeling.

problem Inflexibility and slow sampling in traditional TPP models.
method Triangular Maps and Normalizing Flows for parallel sampling and likelihood computation.
result TriTPP models achieve orders of magnitude faster sampling while maintaining flexibility.

Generative flows learn distributions on low-dimensional manifolds robustly via Wasserstein proximals.

problem Learning distributions supported on low-dimensional manifolds robustly.
method Combining Wasserstein-1 and Wasserstein-2 proximal operators to formulate well-posed continuous-time generative flows.
result The combination of Wasserstein-1 and Wasserstein-2 proximals ensures the well-posedness of generative flows, leading to unique and robust learning.

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.

CLPF models continuous time-series data with improved representational power and variational approximations.

problem Fitting continuous time-series data with existing models faces challenges in representational power and variational quality.
method CLPF uses a time-dependent normalizing flow driven by a stochastic differential equation to decode continuous latent processes into continuous observables. Maximum likelihood optimization is achieved through a novel variational posterior process.
result CLPF outperforms state-of-the-art baselines on synthetic and real-world time-series data.

Let K be an irreducible and reversible Markov kernel on a finite set X. We construct a metric W on the set of probability measures on X and show that with respect to this metric, the law of the continuous time Markov chain evolves as the gradient flow of the entropy. This result is a discrete counterpart of the Wassers…

2011-02-25abs ↗pdf ↗

E-NFs generate molecules and their positions while preserving Euclidean symmetries.

problem Generating molecules with their positions while preserving Euclidean symmetries.
method Integrating E(n) graph neural networks into a differential equation to create an invertible equivariant function.
result E-NFs significantly outperform baselines and existing methods in log-likelihood for particle systems and molecules.

Gradient descent-based optimization methods underpin the parameter training of neural networks, and hence comprise a significant component in the impressive test results found in a number of applications. Introducing stochasticity is key to their success in practical problems, and there is some understanding of the rol…

2019-06-10abs ↗pdf ↗

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.

We introduce a dynamical system which we call the AdaBoost flow. The flow is defined by a system of ODEs with control. We show that three algorithms of the AdaBoost family (i) the AdaBoost algorithm of Schapire and Freund (ii) the arc-gv algorithm of Breiman (iii) the confidence rated prediction of Schapire and Singer …

2011-10-28abs ↗pdf ↗

Proposes a new method for high-dimensional density estimation.

problem Estimating high-dimensional probability density functions efficiently.
method Tensorizing flow method combining tensor-train and flow-based generative modeling.
result Efficiently constructs an approximate density in tensor-train form and trains a flow model to match empirical distribution.

We present a deep generative model, named Monge-Ampère flow, which builds on continuous-time gradient flow arising from the Monge-Ampère equation in optimal transport theory. The generative map from the latent space to the data space follows a dynamical system, where a learnable potential function guides a compressible…

2018-09-26abs ↗pdf ↗

RC flow learns molecular kinetics in low dimensions.

problem Discovering interpretable low-dimensional models of molecular kinetics.
method Normalizing flow for coordinate transformation and Brownian dynamics for kinetics approximation.
result Tractable and trainable model of reduced kinetics in continuous time and space.

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.

Paper formulates particle flow using variational inference and Fisher-Rao gradient flow.

problem Estimating posterior densities in probabilistic models.
method Variational formulation of particle flow, Fisher-Rao gradient flow, Gaussian and Gaussian mixture approximations.
result Gaussian and Gaussian mixture approximations of Fisher-Rao particle flow reduce to Exact Daum and Huang particle flow under linear Gaussian assumptions.

In his 2011 work, Maas has shown that the law of any time-reversible continuous-time Markov chain with finite state space evolves like a gradient flow of the relative entropy with respect to its stationary distribution. In this work we show the converse to the above by showing that if the relative law of a Markov chain…

2014-05-11abs ↗pdf ↗

In this paper, a method of prediction on continuous time series variables from the production or flow -- an LSTM algorithm based on multivariate tuning -- is proposed. The algorithm improves the traditional LSTM algorithm and converts the time series data into supervised learning sequences regarding industrial data's f…

2019-08-09abs ↗pdf ↗

New method accelerates optimization in fixed time, improving convergence rates.

problem Optimization in large-scale data-driven problems.
method Gradient-based optimization framework with fixed-time stable dynamical systems.
result Achieves convergence to the optimizer in a fixed number of iterations, independent of initialization.

Mirror flow optimizes separable data problems, converging to a maximum margin classifier.

problem Optimizing classification problems with separable data using mirror flow.
method Examine mirror flow on linearly separable classification problems, focusing on the horizon function of the mirror potential.
result Mirror flow converges to a maximum margin classifier for separable data under certain conditions.

DFMs enable flow-based models for multimodal discrete and continuous data.

problem Combining discrete and continuous data for generative models.
method Discrete Flow Models (DFMs) using Continuous Time Markov Chains.
result DFMs achieve state-of-the-art co-design performance for protein structure and sequence generation.

CTRNNs improve blood glucose forecasting in ICU, outperforming traditional models.

problem Forecasting blood glucose in ICU with irregular measurements.
method Continuous time autoregressive recurrent neural networks (CTRNNs) using neural ODE or neural flow layers.
result CTRNNs generally outperform traditional autoregressive models in probabilistic forecasting of blood glucose.

We examine optimal execution models that take into account both market microstructure impact and informational costs. Informational footprint is related to order flow and is represented by the trader's influence on the flow imbalance process, while microstructure influence is captured by instantaneous price impact. We …

2014-09-09abs ↗pdf ↗

Muon dynamics study uses spectral Wasserstein flow for optimization stability.

problem Optimizing deep learning models with gradient normalization.
method Introduces Spectral Wasserstein distances for matrix flows, proving equivalence with Benamou--Brenier formulation.
result Gradient-flow interpretation of mean-field normalized training dynamics.

Stochastic mirror descent improves performance on ensemble models.

problem Improving performance of ensemble models using stochastic mirror descent.
method Utilizes mirror potential to influence training algorithm's implicit bias, mapping evolution to continuous time process.
result Converges to a nonlinear PDE in asymptotic regime of large networks, with mirror potential affecting gradient flow.

Continuous-time mirror descent solves sparse phase retrieval efficiently.

problem Recovering sparse signals from magnitude-only measurements.
method Continuous-time mirror descent applied to unconstrained empirical risk minimization problem.
result Mirror descent recovers kk-sparse vectors with minimum non-zero entry order of x2/k\| \mathbf{x}^\star \|_2/\sqrt{k} from k2k^2 Gaussian measurements.