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

98195293390 · Jun 202019922001200920172026
48 results for linear diffusion

Theoretical justification for image inpainting using diffusion models.

problem Improving sample recovery in image inpainting without retraining.
method Analysis of RePaint algorithm and proposing RePaint+^+ to correct misalignment.
result RePaint+^+ algorithm provably recovers the true sample with linear convergence.

New method uses diffusion models for Bayesian inverse problems.

problem Solving Bayesian inverse problems with linear-Gaussian models.
method Decoupled Diffusion Sequential Monte Carlo (DDSMC) method.
result Asymptotically exact solution demonstrated on various data types.

Diffusion models generate data with Gaussian Universality, matching linear model test errors.

problem Analyzing the performance of models trained on synthetic data generated by diffusion models.
method Investigates Gaussian Universality for data distributions generated via diffusion models, matching test errors of linear models trained on synthetic data to Gaussian Mixture models.
result The test error of a linear model trained on diffusion-generated data matches the test error of a linear model trained on Gaussian Mixture data with matching means and covariances per class.

A new algorithm improves posterior sampling for linear inverse problems.

problem Efficiently sampling from posterior distributions in noisy linear inverse problems.
method Proposes \pddim, a DDIM-type sampler that separately samples along singular directions of the measurement operator.
result The method converges to the Bayesian posterior conditioned on the measurements.

New method speeds up diffusion models inference to sub-linear time.

problem Efficient inference of diffusion models for high-dimensional data.
method Parallel sampling with Picard iterations within blocks.
result Achieves sub-linear time complexity of O~(polylogd)\widetilde{\mathcal{O}}(\mathrm{poly} \log d).

A fast method approximates likelihood scores for noisy linear inverse problems.

problem Solving noisy linear inverse problems efficiently.
method Proposes a simple closed-form approximation to the likelihood score for diffusion and flow-based models.
result Significantly faster than baseline methods while maintaining competitive or better reconstruction performances.

Develops polynomial diffusion models for multi-factor commodity futures dynamics.

problem Modeling futures prices using latent state variables for short and long-term stochastic factors.
method Polynomial diffusion models to incorporate non-linear effects, two filtering methods for estimation.
result Accurate estimation of futures prices despite parameter identification issues in polynomial diffusion models.

This paper conditions non-linear infinite-dimensional diffusion processes.

problem Conditioning non-linear and infinite-dimensional diffusion processes.
method Infinite-dimensional Girsanov's theorem to condition function-valued stochastic processes.
result Conditioning of non-linear infinite-dimensional diffusion processes is achieved.

GF-Net learns Green's functions for linear reaction-diffusion equations.

problem Learning Green's functions for linear reaction-diffusion equations on arbitrary domains.
method GF-Net, a neural network, learns Green's functions in an unsupervised manner using physics-informed approach and symmetry.
result GF-Net efficiently solves linear reaction-diffusion equations under various boundary conditions and sources.

Diffusion means converge to extrinsic means for long times on spheres.

problem Understanding the long-time behavior of diffusion means on manifolds.
method Introduced diffusion means as a parameterized family of location statistics on manifolds, and analyzed their convergence to extrinsic means for long times.
result For real projective spaces and connected compact symmetric spaces, the long-time limit of diffusion means is conjectured to be the extrinsic mean in the isometric embedding.

This work connects diffusion models to power iteration, revealing how low frequencies emerge earlier.

problem Understanding the generation process of diffusion models and their relation to power iteration.
method Examined the linear case of diffusion models, connecting them to the spiked covariance model and power iteration.
result Linear diffusion models converge to the leading eigenvector, similar to power iteration.

Diffusion models generalize better with hierarchical data structure and regularization.

problem Understanding generalization in diffusion models with finite data.
method Analyzing diffusion models through data covariance spectra and developing a theoretical framework based on linear neural networks.
result Generalization in diffusion models improves with hierarchical data structure and regularization.

First, classes of Markov processes that scale exactly with a Hurst exponent H are derived in closed form. A special case of one class is the Tsallis density, advertised elsewhere as nonlinear diffusion or diffusion with nonlinear feedback. But the Tsallis model is only one of a very large class of linear diffusion with…

2006-06-05abs ↗pdf ↗

Diffusion maps are an emerging data-driven technique for non-linear dimensionality reduction, which are especially useful for the analysis of coherent structures and nonlinear embeddings of dynamical systems. However, the computational complexity of the diffusion maps algorithm scales with the number of observations. T…

2018-02-23abs ↗pdf ↗

Study shows how diffusion models learn on low-dimensional manifolds.

problem Learning efficiency of diffusion models on manifolds.
method Analyzes denoising score matching with random feature neural networks.
result Sample complexity scales linearly with intrinsic dimension, not ambient dimension.

Diffusion models' consistency across splits explained by random matrix theory.

problem Consistency of diffusion models trained on non-overlapping subsets.
method Random matrix theory framework to quantify dataset effects on denoiser and sampling map.
result The theory explains and predicts cross-split disagreement in diffusion models.

We present new extensions to a method for constructing several families of solvable one-dimensional time-homogeneous diffusions whose transition densities are obtainable in analytically closed-form. Our approach is based on a dual application of the so-called diffusion canonical transformation method that combines smoo…

2009-07-16abs ↗pdf ↗

Develops new bounds for deterministic samplers in diffusion models.

problem Analyzing deterministic samplers in diffusion generative models.
method Operational interpretation of deterministic sampling; restoration and degradation steps.
result First polynomial convergence bounds for DDIM-type samplers.

Method infers parameters in complex diffusion processes.

problem Parameter inference in high-dimensional, non-linear diffusion processes.
method Differentiable score matching to approximate diffusion bridges, used in an importance sampler.
result Numerically stable framework for parameter inference and diffusion mean estimation.

Automates learning of multivariate diffusions for generative models.

problem Lack of automated methods for choosing and optimizing diffusion processes in generative models.
method Develops a recipe to maximize likelihood without model-specific analysis, parameterizes diffusion for target noise, and optimizes the inference diffusion process.
result Automatic search over all linear diffusions for generative models.

Improved generative models for rare events using nonlinear diffusion.

problem Challenges in modeling rare conditional distributions with linear diffusion models.
method Adapting data representation and forward scheme for nonlinear drift term.
result Significant improvement in capturing extreme tail events.

Study on policy gradient for stochastic bandits using diffusion approximation.

problem Improving policy gradient methods for stochastic bandits with optimal regret bounds.
method Continuous-time diffusion approximation of policy gradient with learning rate analysis.
result Proved optimal regret bound of O(klog(k)log(n)/η)O(k \log(k) \log(n) / η) for η=O(Δ2/log(n))η= O(Δ^2/\log(n)).

Paper analyzes latent space geometry in generative models using Fisher information.

problem Understanding the structure of latent spaces in generative models.
method Reconstructs Fisher information metric from generated samples and posterior distribution.
result Reveals fractal structure and abrupt changes in Fisher metric at phase boundaries.

Diffusion models learn simple statistics before complex ones, revealing a sample complexity exponent.

problem Understanding the learning dynamics of diffusion models.
method Empirical observations and theoretical analysis of diffusion models and denoisers.
result Diffusion models learn simple statistics (pair-wise correlations) at linear sample complexity, while higher-order statistics (e.g., fourth cumulant) require cubic sample complexity.

Study shows how to control jump-diffusion processes with stable feedback controls in reinforcement learning.

problem Control jump-diffusion processes with unknown coefficients in reinforcement learning.
method Lipschitz continuous optimal feedback controls, stability analysis of forward-backward SDEs, least-squares algorithm.
result Achieves O(NlnN)O(\sqrt{N\ln N}) regret for linear-convex learning problems with jumps.

Iterative tilting fine-tunes diffusion models for reward-tilted distributions.

problem Fine-tuning diffusion models for reward-tilted distributions.
method Decomposes large reward tilts into smaller, tractable tilts via first-order Taylor expansion, avoiding backpropagation.
result Validated on a two-dimensional Gaussian mixture, achieving exact closed-form solutions.

We investigate which jump-diffusion models are convexity preserving. The study of convexity preserving models is motivated by monotonicity results for such models in the volatility and in the jump parameters. We give a necessary condition for convexity to be preserved in several-dimensional jump-diffusion models. This …

2006-01-22abs ↗pdf ↗

This paper improves diffusion models for low-dimensional data.

problem Theoretical foundations of diffusion models are lacking for low-dimensional data.
method Score approximation, estimation, and distribution recovery of diffusion models on low-dimensional data.
result Sample complexity bounds for distribution estimation using diffusion models are provided.

A new diffusion sampling method combines Krylov subspace and diffusion models for faster and more efficient inverse problems.

problem Efficiently solving large-scale inverse problems in high-performance computing.
method Proposes a novel diffusion sampling strategy that integrates Krylov subspace methods with diffusion models.
result Demonstrates significant speedup (80x faster inference time) and improved reconstruction quality on real-world medical imaging problems.

Proposes efficient sampling methods for solving linear inverse problems.

problem Solving linear inverse problems with computational efficiency and accuracy.
method Higher-order Langevin diffusion with pre-conditioning and annealing.
result Provable sampling from posterior distributions with accelerated convergence.

StrADiff separates sources from mixtures without labels, using structured priors.

problem Blind source separation of linear and nonlinear mixtures without labeled data.
method Structured Source-Wise Adaptive Diffusion Framework with Gaussian process priors.
result StrADiff can recover latent source trajectories in an unsupervised manner, especially stable in linear mixtures.