Efficiently reconstructs jump-diffusion processes from data using neural networks.
problem Reconstructing jump-diffusion processes from data.
method Temporally decoupled squared Wasserstein distance method using parameterized neural networks.
result Enhanced reconstruction of jump-diffusion processes from data.
Extends neural diffusion processes for multi-task regression.
problem Limited to single-task inference, existing formulations cannot capture dependencies across related tasks.
method Introduces a task encoder to condition diffusion model on low-dimensional representations of context observations.
result Improves predictive performance and uncertainty calibration across related functions.
NDPs learn to sample from complex function distributions using neural networks and diffusion models.
problem Learning rich distributions over functions with neural networks.
method NDPs use denoising diffusion models and custom attention blocks to incorporate stochastic process properties.
result NDPs can capture functional distributions close to true Bayesian posteriors and outperform neural processes.
Neural Flow Diffusion Models improve diffusion models by learning flexible forward processes.
problem Fixed forward processes in diffusion models complicate reverse processes and increase inference costs.
method Introduces NFDM, a framework supporting flexible forward processes and a novel parameterization technique.
result Demonstrates strong performance in likelihood estimation and learning generative dynamics.
Neural network approximates diffusion bridges for efficiency and robustness.
problem Efficient simulation of conditioned diffusion processes, especially rare events and multimodal distributions.
method Trains a neural network to approximate bridge dynamics, eliminating MCMC and score modeling.
result Efficient sampling of conditioned diffusion bridges at comparable cost to unconditioned process.
Neural Diffusion Intensity Models simplify Cox processes inference.
problem Intractable nonparametric estimation and posterior inference of latent stochastic intensity in Cox processes.
method Variational framework using neural SDEs, with theoretical guarantee of ELBO maximization coinciding with maximum likelihood estimation.
result Accurate recovery of latent intensity dynamics and posterior paths with significant speedup.
The paper develops a neural network method for estimating drift functions of diffusion processes from discrete observations.
problem Nonparametric estimation of drift function for diffusion processes from high-frequency discrete observations.
method Neural network-based estimator for drift function estimation.
result Derives a non-asymptotic convergence rate for the neural network estimator.
The paper develops a neural network-based classifier for diffusion process drifts.
problem Classifying diffusion processes with distinct drift functions from discrete observations.
method Derives a Bayes rule and constructs a plug-in classifier using neural networks to estimate drifts.
result Establishes convergence rates for misclassification risk, highlighting benefits of diffusion structure.
DEMOTE uses neural diffusion-reaction processes to capture temporal dynamics in sparse tensor data.
problem Sparse and temporally associated tensor data with limited structural knowledge.
method Develops a neural diffusion-reaction process to estimate dynamic embeddings for tensor modes.
result Captures both commonalities and personalities in evolving tensor entries.
New method bypasses time-reversal for diffusion-based generative models.
problem Diffusion-based generative models require time-reversal, limiting flexibility.
method Constructs diffusion processes without time-reversal through mixtures of diffusion bridges.
result Exact transport without time-reversal, greater flexibility in dynamics.
Proposes LDIDPs for efficient sequential data generation from latent dynamical models.
problem Challenges in generating high-fidelity sequential samples from latent dynamical models.
method Utilizes implicit diffusion processes to sample from latent dynamical processes.
result Demonstrates accurate learning of dynamics and efficient generation of high-quality sequential data.
NCS enables efficient and accurate conditional simulation for complex spatial processes.
problem Challenges in simulating from complex spatial process distributions.
method Neural diffusion models and conditional score-based diffusion.
result NCS outperforms traditional methods in efficiency and accuracy.
Paper proposes a new method for training diffusion models using Markov operators.
problem Training efficiency and accuracy in diffusion models.
method Operator-informed score matching using spectral decomposition of Markov operators.
result Improved score matching for both low and high-dimensional distributions.
MINDE estimates Mutual Information using neural diffusion models.
problem Estimating Mutual Information between random variables.
method Score-based diffusion models to estimate Kullback Leibler divergence.
result MINDE is more accurate than existing methods, especially for challenging distributions.
This paper extends neural network approximation results to denoising diffusion models.
problem Improving the efficiency and accuracy of generative models.
method Leveraging connections to stochastic control and neural network approximation.
result Established neural network approximation results for the Föllmer drift are extended to denoising diffusion models.
SpecGrad improves neural vocoder sound quality by adapting diffusion noise to log-mel spectrogram.
problem Improving neural vocoder sound quality, especially in high-frequency bands.
method Adapting the diffusion noise distribution to the conditioning log-mel spectrogram through time-varying filtering.
result SpecGrad generates higher-fidelity speech waveform than conventional DDPM-based neural vocoders.
Parameter inference for stochastic differential equations is challenging due to the presence of a latent diffusion process. Working with an Euler-Maruyama discretisation for the diffusion, we use variational inference to jointly learn the parameters and the diffusion paths. We use a standard mean-field variational appr…
Improved language generation with faster sampling speed.
problem Speed and coherence issues in autoregressive language models.
method Introduces Neural Flow Diffusion Models (NFDM) for discrete state spaces.
result Substantially reduces likelihood gap with autoregressive models.
PTSD improves neural samplers by combining diffusion models and PT, enhancing efficiency.
problem Efficiency and correlation issues in neural samplers compared to PT.
method Sequential training of diffusion models across temperatures, combining high-temperature models for approximate lower-temperature samples.
result Significantly improved target evaluation efficiency, outperforming diffusion-based samplers.
Extends diffusion models to non-Euclidean spaces with geometric priors.
problem Difficulties in natural sciences with symmetries and non-Euclidean data.
method Constructs a noising process and neural network equivariant to symmetry group, approximates score function.
result Model can generate complex scalar and vector fields on synthetic and real-world data.
The Backpropagation algorithm relies on the abstraction of using a neural model that gets rid of the notion of time, since the input is mapped instantaneously to the output. In this paper, we claim that this abstraction of ignoring time, along with the abrupt input changes that occur when feeding the training set, are …
When the parameters are independently and identically distributed (initialized) neural networks exhibit undesirable properties that emerge as the number of layers increases, e.g. a vanishing dependency on the input and a concentration on restrictive families of functions including constant functions. We consider parame…
In deep latent Gaussian models, the latent variable is generated by a time-inhomogeneous Markov chain, where at each time step we pass the current state through a parametric nonlinear map, such as a feedforward neural net, and add a small independent Gaussian perturbation. This work considers the diffusion limit of suc…
New method learns diffusion transition density for Bayesian inference.
problem Bayesian inference on diffusions with inaccessible boundaries.
method Neural Galerkin framework to solve FP equation with Dirac mass.
result Approximates likelihood function for efficient posterior sampling.
Nonlocal neural networks have been proposed and shown to be effective in several computer vision tasks, where the nonlocal operations can directly capture long-range dependencies in the feature space. In this paper, we study the nature of diffusion and damping effect of nonlocal networks by doing spectrum analysis on t…
GRAND treats GNNs as PDE discretizations, addressing graph learning issues.
problem Graph learning issues like depth, oversmoothing, and bottlenecks.
method Models GNNs as a continuous diffusion process, treating them as PDE discretizations.
result Linear and nonlinear versions of GRAND achieve competitive results on graph benchmarks.
Framework for energy markets using measure-valued processes.
problem Arbitrage-free modeling of energy futures markets.
method Translation of Heath-Jarrow-Morton approach to measure-valued processes, derivation of HJM-drift condition, analysis of measure-valued diffusions.
result Existence of non-negative measure-valued diffusions satisfying the HJM-drift condition.
Social recommendation has emerged to leverage social connections among users for predicting users' unknown preferences, which could alleviate the data sparsity issue in collaborative filtering based recommendation. Early approaches relied on utilizing each user's first-order social neighbors' interests for better user …
The paper develops a computational method for efficient online filtering of diffusion processes.
problem Online filtering of discretely observed nonlinear diffusion processes.
method The approach involves Doob's h-transforms approximated by solving backward Kolmogorov equations using nonlinear Feynman-Kac formulas and neural networks. result The proposed method can be orders of magnitude more efficient than state-of-the-art particle filters.
This paper uses diffusion models for lossy image compression, improving perceptual metrics and practicality.
problem Lossy image compression with improved perceptual metrics and practicality.
method End-to-end optimized lossy image compression using conditional diffusion models.
result The model yields stronger FID scores and competitive performance in distortion metrics.
Fairness-aware diffusion for graph neural networks
problem Fairness in graph neural networks
method Adapting diffusion process with fairness-aware modifications
result Improves fairness metrics with minimal additional cost
In this paper, we study the problem of using representation learning to assist information diffusion prediction on graphs. In particular, we aim at estimating the probability of an inactive node to be activated next in a cascade. Despite the success of recent deep learning methods for diffusion, we find that they often…
Faster sampling in discrete diffusion models with predetermined transition time.
problem Efficiency in sampling discrete diffusion models.
method Discrete Non-Markov Diffusion Models (DNDM) with predetermined transition time.
result Significantly reduces the number of function evaluations for faster sampling.
CDS combines PT and diffusion for efficient sampling from multimodal distributions.
problem Sampling from unnormalized multimodal distributions efficiently.
method Conditional Diffusion Sampling (CDS) using Conditional Interpolants and Parallel Tempering.
result CDS achieves a superior trade-off between sample quality and density evaluation cost.
Improved text-conditioned regression using LLMs and diffusion-based neural processes.
problem Major error cascades and computational inefficiency in LLMs for short sequences.
method Combining LLM predictive densities with a diffusion-based neural process.
result Better-calibrated predictions and locally consistent trajectories.
The paper analyzes statistical guarantees for denoising reflected diffusion models.
problem The mismatch between theoretical design and implementation of diffusion models introduces issues in high-dimensional target data.
method The paper uses a reflected diffusion process as the driver of noise and establishes rates of convergence in total variation.
result The statistical guarantees for denoising reflected diffusion models match the minimax lower bound up to a polylogarithmic factor.
DPS uses PINNs to estimate drift in diffusion models for sampling.
problem Accurately estimating drift term in reverse SDE from unnormalized density.
method Diffusion-PINN Sampler (DPS) solves PINN for log-density of SDE marginals.
result DPS achieves convergence guarantees and accurately samples complex distributions.
Unified framework for inference in complex nonlinear processes.
problem Challenges in inferring nonlinear continuous stochastic processes with sparse observations and complex topologies.
method Neural Backward Filtering Forward Guiding (NBFFG) framework that constructs a variational posterior using a proxy linear-Gaussian process.
result Empirical results show NBFFG outperforms baselines on synthetic benchmarks and high-dimensional phylogenetic analysis tasks.
ADD-THIN improves TPP forecasting by handling long-term data sequences.
problem Sequential limitations in autoregressive models for TPPs.
method Diffusion model for TPPs that operates on entire sequences.
result ADD-THIN outperforms state-of-the-art models in forecasting.
A new graph generator uses heat diffusion on graph Laplacians to create new graph structures.
problem Creating realistic and diverse graph structures for various applications.
method Adapting the Generator Matching paradigm to graph data, using graph Laplacian and heat kernel for diffusion.
result The method effectively generates graphs with structural properties of real and synthetic graphs.
We use GANs and signatures to approximate conditional laws in filtering and prediction of diffusion processes.
problem Approximating conditional laws for diffusion processes with noisy observations.
method Conditional GANs combined with signatures for approximation.
result Efficient approximation of conditional laws for diffusion processes.
Graph neural networks are explained through heat diffusion analogy.
problem Limitations of graph neural networks (oversmoothing, oversquashing).
method Analogizing message passing in GNNs to heat dynamics.
result Fundamental understanding of GNNs and improved model design.
This work proposes a geometric approach to equivariant message passing on Riemannian manifolds.
problem Efficiently processing data on Riemannian manifolds with equivariance.
method Geometric insight into equivariant message passing on Riemannian manifolds, using an equivariant embedding and diffusion process.
result A new class of equivariant GNNs on Riemannian manifolds.
New method DDVI improves posterior inference for deep Gaussian processes.
problem Inference of inducing points in DGPs is challenging and biased.
method DDVI uses denoising diffusion SDE and score matching for posterior approximation.
result Empirically shows DDVI outperforms baseline methods in inducing point inference.
NDMs enable non-linear transformations in diffusion models for better generative tasks.
problem Limited to linear transformations, diffusion models struggle with generative tasks.
method Presented NDMs that allow time-dependent non-linear transformations.
result NDMs outperform conventional diffusion models in likelihood and sample quality.
A new criterion for deep active learning selects minimal labeled data points.
problem Efficiently select minimal labeled data points for deep neural networks.
method Diffuses label information over a graph of data representations to switch between exploration and refinement.
result The diffusion-based criterion outperforms existing methods in deep active learning.
The study examines how shallow neural nets converge to training samples or manifold points during diffusion.
problem Understanding when and how shallow neural nets converge to training samples or manifold points during diffusion.
method Analysis of shallow ReLU neural network denoisers trained with minimal ℓ2 norm, comparing score flow and diffusion flow. result Probability flow converges to training points, sums of training points, or manifold points, depending on the diffusion time scheduler.
AdaCAD improves semi-supervised classification by focusing on intra-class nodes.
problem Improving semi-supervised classification by addressing inter-class connections in graphs.
method AdaCAD uses a class-attentive diffusion process to adaptively aggregate nodes based on their class similarity.
result AdaCAD significantly outperforms state-of-the-art methods in semi-supervised classification.