Nearly d-linear convergence bounds for diffusion models via stochastic localization

Nearly d-linear convergence bounds for diffusion models via stochastic localization

Denoising diffusions are a powerful method to generate approximate samples from high-dimensional data distributions. Recent results provide polynomial bounds on their convergence rate, assuming L 2 -accurate scores. Until now, the tightest bounds were either superlinear in the data dimension or requ...

Bibliografske podrobnosti
Main Authors:	Benton, J, Bortoli, VD, Doucet, A, Deligiannidis, G
Format:	Conference item
Jezik:	English
Izdano:	OpenReview 2024

Podobne knjige/članki

Error bounds for flow matching methods
od: Benton, J, et al.
Izdano: (2024)

A continuous time framework for discrete denoising models
od: Campbell, A, et al.
Izdano: (2023)

Linear bounds for stochastic dispersion
od: Cranston, M, et al.
Izdano: (2000)

Chained generalisation bounds
od: Clerico, E, et al.
Izdano: (2022)

Convergence to Stochastic Integrals with Non-linear integrands.
od: Caceres, C, et al.
Izdano: (2007)

Diffusion Schrödinger bridge with applications to score-based generative modeling
od: De Bortoli, V, et al.
Izdano: (2022)

Stochastic convergence /
od: 389129 Lukacs, Eugene
Izdano: (1975)

Stochastic convergence of weighted sums of random elements in linear spaces /
od: 403151 Taylor, Robert Lee
Izdano: (1978)

Cramér-Rao Bounds for Near-Field Localization
od: de Jesus Torres, Andrea, et al.
Izdano: (2022)

Near-linear convergence of the Random Osborne algorithm for Matrix Balancing
od: Altschuler, Jason M., et al.
Izdano: (2022)

Tight global linear convergence rate bounds for operator splitting methods
od: Banjac, G, et al.
Izdano: (2018)

Randomized Hamiltonian Monte Carlo as scaling limit of the bouncy particle sampler and dimension-free convergence rates
od: Deligiannidis, G, et al.
Izdano: (2021)

Randomized Hamiltonian Monte Carlo as scaling limit of the bouncy particle sampler and dimension-free convergence rates
od: Deligiannidis, G, et al.
Izdano: (2020)

DIFFUSIVITY BOUNDS FOR 1D BROWNIAN POLYMERS
od: Tarres, P, et al.
Izdano: (2012)

Bounds on Linear PDEs via Semidefinite Optimization
od: Bertsimas, Dimitris J., et al.
Izdano: (2003)

On local linear approximations to diffusion processes
od: Duan, X, et al.
Izdano: (2011)

Convergence of an Euler scheme for a hybrid stochastic-local volatility model with stochastic rates in foreign exchange markets
od: Cozma, A, et al.
Izdano: (2018)

A PHASE PLANE DISCUSSION OF CONVERGENCE TO TRAVELING FRONTS FOR NON-LINEAR DIFFUSION
od: Fife, P, et al.
Izdano: (1981)

How descriptive are GMRES convergence bounds?
od: Embree, M
Izdano: (1999)

Stabilization of Stochastic Iterative Methods for Singular and Nearly Singular Linear Systems
od: Wang, Mengdi, et al.
Izdano: (2015)

Convergence rate analysis of a stochastic trust-region method via supermartingales
od: Blanchet, J, et al.
Izdano: (2019)

Convergence of policy gradient methods for finite-horizon stochastic linear-quadratic control problems
od: Giegrich, M, et al.
Izdano: (2024)

Differentiable particle filtering via entropy-regularized optimal transport
od: Corenflos, A, et al.
Izdano: (2021)

Convergence of stochastic nonlinear systems and implications for Stochastic Model Predictive Control
od: Muñoz-Carpintero, D, et al.
Izdano: (2020)

Convergence of Stochastic Proximal Gradient Algorithm
od: Rosasco, Lorenzo, et al.
Izdano: (2021)

Stochastic sampling algorithms for state estimation of jump Markov linear systems
od: Doucet, A, et al.
Izdano: (2000)

The topology of uniform convergence on order-bounded sets /
od: 463259 Wong, Yau-Chuen
Izdano: (1976)

Improved bounds for randomly sampling colorings via linear programming
od: Moitra, Ankur, et al.
Izdano: (2021)

Deriving lower bounds on the efficiency of near-degenerate thermal machines via synchronization
od: Murtadho, Taufiq, et al.
Izdano: (2023)

Convergence of iterations for linear equations /
od: 253107 Nevanlinna, Olavi
Izdano: (1993)

Efficient stochastic simulation of reaction-diffusion processes via direct compilation
od: Lis, Mieszko, et al.
Izdano: (2010)

On the Convergence of Stochastic Iterative Dynamic Programming Algorithms
od: Jaakkola, Tommi, et al.
Izdano: (2004)

On the convergence of stochastic MPC to terminal modes of operation
od: Munoz-Carpintero, D, et al.
Izdano: (2019)

Global Continuous Optimization with Error Bound and Fast Convergence
od: Maruyama, Yu, et al.
Izdano: (2017)

Scalar curvature lower bound under integral convergence
od: Huang, Yiqi, et al.
Izdano: (2022)

Rates of convergence in normal approximation under moment conditions via new bounds on solutions of the Stein equation
od: Gaunt, R
Izdano: (2014)

Inference for Levy-Driven Stochastic Volatility Models via Adaptive Sequential Monte Carlo
od: Jasra, A, et al.
Izdano: (2011)

On the stochastic modelling of reaction-diffusion processes
od: Twomey, A
Izdano: (2007)

Stochastic learning dynamics and speed of convergence in population games
od: Arieli, I, et al.
Izdano: (2016)

Stochastic learning dynamics and speed of convergence in population games
od: Young, H, et al.
Izdano: (2015)