Fetching the paper…
Reading the bibliography…
How diffusion models generalize beyond their training set is not known, and is somewhat mysterious given two facts: the optimum of the denoising score matching (DSM) objective usually used to train diffusion models is the score function of the training distribution; and the networks usually used to learn the score function are expressive enough to learn this score to high accuracy.
Statistical dynamics of classical systems
P. C. Martin, E. D. Siggia, and H. A. Rose · 1973
Earlier work this paper cites.
Path integrals in quantum mechanics, statistics, polymer physics, and financial markets
Hagen Kleinert · 2006
Earlier work this paper cites.
A connection between score matching and denoising autoencoders
Pascal Vincent · 2011
Earlier work this paper cites.
Deep unsupervised learning using nonequilibrium thermodynamics
Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli · 2015
Earlier work this paper cites.
Group equivariant convolutional networks
Taco Cohen and Max Welling · 2016
Earlier work this paper cites.
Understanding deep learning requires rethinking generalization
Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, and Oriol Vinyals · 2017
Earlier work this paper cites.
Neural ordinary differential equations
Ricky T. Q. Chen, Yulia Rubanova, Jesse Bettencourt, and David K Duvenaud · 2018
Earlier work this paper cites.
Path integral approach to random neural networks
A. Crisanti and H. Sompolinsky · 2018
Earlier work this paper cites.
Neural tangent kernel: Convergence and generalization in neural networks
Arthur Jacot, Franck Gabriel, and Clement Hongler · 2018
Earlier work this paper cites.
A bayesian perspective on generalization and stochastic gradient descent
Samuel L. Smith and Quoc V. Le · 2018
Earlier work this paper cites.
On exact computation with an infinitely wide neural net
Sanjeev Arora, Simon S Du, Wei Hu, Zhiyuan Li, Russ R Salakhutdinov, and Ruosong Wang · 2019
Earlier work this paper cites.
On the inductive bias of neural tangent kernels
Alberto Bietti and Julien Mairal · 2019
Earlier work this paper cites.
On lazy training in differentiable programming
Lénaïc Chizat, Edouard Oyallon, and Francis Bach · 2019
Earlier work this paper cites.
On the spectral bias of neural networks
Nasim Rahaman, Aristide Baratin, Devansh Arpit, Felix Draxler, Min Lin, Fred Hamprecht, Yoshua Bengio, and Aaron Courville · 2019
Earlier work this paper cites.
Generative modeling by estimating gradients of the data distribution
Yang Song and Stefano Ermon · 2019
Earlier work this paper cites.
Spectrum dependent learning curves in kernel regression and wide neural networks
Blake Bordelon, Abdulkadir Canatar, and Cengiz Pehlevan · 2020
Earlier work this paper cites.
Disentangling feature and lazy training in deep neural networks
Mario Geiger, Stefano Spigler, Arthur Jacot, and Matthieu Wyart · 2020
Earlier work this paper cites.
Denoising diffusion probabilistic models
Jonathan Ho, Ajay Jain, and Pieter Abbeel · 2020
Cited alongside, same era.
Dynamical mean-field theory for stochastic gradient descent in gaussian mixture classification
Francesca Mignacco, Florent Krzakala, Pierfrancesco Urbani, and Lenka Zdeborová · 2020
Cited alongside, same era.
On the generalization benefit of noise in stochastic gradient descent
Samuel Smith, Erich Elsen, and Soham De · 2020
Cited alongside, same era.
Sliced score matching: A scalable approach to density and score estimation
Yang Song, Sahaj Garg, Jiaxin Shi, and Stefano Ermon · 2020
Cited alongside, same era.
Kernel and rich regimes in overparametrized models
Blake Woodworth, Suriya Gunasekar, Jason D. Lee, Edward Moroshko, Pedro Savarese, Itay Golan, Daniel Soudry, and Nathan Srebro · 2020
Cited alongside, same era.
Diffusion schrödinger bridge with applications to score-based generative modeling
The probability flow ode is provably fast
Sitan Chen, Sinho Chewi, Holden Lee, Yuanzhi Li, Jianfeng Lu, and Adil Salim · 2023
Later among the works it cites.
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
George Stein, Jesse C. Cresswell, Rasa Hosseinzadeh, Yi Sui, Brendan Leigh Ross, Valentin Villecroze, Zhaoyan Liu, Anthony L. Caterini, Eric Taylor, and Gabriel Loaiza-Ganem · 2023
Later among the works it cites.
On provable copyright protection for generative models
Nikhil Vyas, Sham M. Kakade, and Boaz Barak · 2023
Later among the works it cites.
Diffusion models generate images like painters: an analytical theory of outline first, details later
Binxu Wang and John J. Vastola · 2023
Later among the works it cites.
Stable target field for reduced variance score estimation in diffusion models
Yilun Xu, Shangyuan Tong, and Tommi S. Jaakkola · 2023
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Valentin De Bortoli, James Thornton, Jeremy Heng, and Arnaud Doucet · 2021
Cited alongside, same era.
Score-based generative modeling through stochastic differential equations
Yang Song, Jascha Sohl-Dickstein, Diederik P Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole · 2021
Cited alongside, same era.
Self-consistent dynamical field theory of kernel evolution in wide neural networks
Blake Bordelon and Cengiz Pehlevan · 2022
Cited alongside, same era.
Convergence of denoising diffusion models under the manifold hypothesis
Valentin De Bortoli · 2022
Cited alongside, same era.
Denoising likelihood score matching for conditional score-based data generation
Chen-Hao Chao, Wei-Fang Sun, Bo-Wun Cheng, Yi-Chen Lo, Chia-Che Chang, Yu-Lun Liu, Yu-Lin Chang, Chia-Ping Chen, and Chun-Yi Lee · 2022
Cited alongside, same era.
Elucidating the design space of diffusion-based generative models
Tero Karras, Miika Aittala, Timo Aila, and Samuli Laine · 2022
Cited alongside, same era.
Pseudo numerical methods for diffusion models on manifolds
Luping Liu, Yi Ren, Zhijie Lin, and Zhou Zhao · 2022
Cited alongside, same era.
Diffusion models: A comprehensive survey of methods and applications
Ling Yang, Zhilong Zhang, Yang Song, Shenda Hong, Runsheng Xu, Yue Zhao, Wentao Zhang, Bin Cui, and Ming-Hsuan Yang · 2023
Later among the works it cites.
Diffusion probabilistic models generalize when they fail to memorize
TaeHo Yoon, Joo Young Choi, Sehyun Kwon, and Ernest K. Ryu · 2023
Later among the works it cites.
Investigating data memorization in 3d latent diffusion models for medical image synthesis
Salman Ul Hassan Dar, Arman Ghanaat, Jannik Kahmann, Isabelle Ayx, Theano Papavassiliu, Stefan O. Schoenberg, and Sandy Engelhardt · 2024
Later among the works it cites.
Neural network-based score estimation in diffusion models: Optimization and generalization
Yinbin Han, Meisam Razaviyayn, and Renyuan Xu · 2024
Later among the works it cites.
Generalization in diffusion models arises from geometry-adaptive harmonic representations
Zahra Kadkhodaie, Florentin Guth, Eero P Simoncelli, and Stéphane Mallat · 2024
Later among the works it cites.
An analytic theory of creativity in convolutional diffusion models
Mason Kamb and Surya Ganguli · 2024
Later among the works it cites.
Analyzing and improving the training dynamics of diffusion models, 2024
Tero Karras, Miika Aittala, Jaakko Lehtinen, Janne Hellsten, Timo Aila, and Samuli Laine · 2024
Later among the works it cites.
Boomerang: Local sampling on image manifolds using diffusion models
Lorenzo Luzi, Paul M Mayer, Josue Casco-Rodriguez, Ali Siahkoohi, and Richard Baraniuk · 2024
Later among the works it cites.
The unreasonable effectiveness of gaussian score approximation for diffusion models and its applications
Binxu Wang and John Vastola · 2024
Later among the works it cites.
The emergence of reproducibility and consistency in diffusion models
Huijie Zhang, Jinfan Zhou, Yifu Lu, Minzhe Guo, Peng Wang, Liyue Shen, and Qing Qu · 2024
Later among the works it cites.
Towards a mechanistic explanation of diffusion model generalization
Matthew Niedoba, Berend Zwartsenberg, Kevin Murphy, and Frank Wood · 2025
Closest in time.
Spectral bias and task-model alignment explain generalization in kernel regression and infinitely wide neural networks
Abdulkadir Canatar, Blake Bordelon, and Cengiz Pehlevan · 2041
Closest in time.