Arpit Bansal, Eitan Borgnia, Hong-Min Chu
Jie S. Li, Hamid Kazemi, Furong Huang, Micah Goldblum, Jonas Geiping, Tom Goldstein
2022 · arXiv
Standard diffusion models involve an image transform -- adding Gaussian noise -- and an image restoration operator that inverts this degradation. We observe that the generative behavior of diffusion models is not strongly dependent on the choice of image degradation, and in fact an entire family of generative models can be constructed by varying this choice. Even when using completely deterministic degradations (e.g., blur, masking, and more), the training and test-time update rules that underlie diffusion models can be easily generalized to create generative models. The success of these fully deterministic models calls into question the community's understanding of diffusion models, which relies on noise in either gradient Langevin dynamics or variational inference, and paves the way for generalized diffusion models that invert arbitrary processes. Our code is available at https://github.com/arpitbansal297/Cold-Diffusion-Models
Metadata: arXiv. Abstracts retain their original authors’ rights.
Original HN comments, with labels from simple text rules. A label describes the whole comment and may miss context or irony. Read the discussion to make up your own mind. About the labels
3 selected excerpts · 3 total mentions
I wrote a response yesterday but did not post it or send it, ops. I still don't understand the problem, if you ask model trained on a noise pattern "trees" for a forest it will still give you a random forest, that's what it was trained on, also: https://arxiv.org/abs/2208.09392, to see the diffusion process applied to processes other than Gaussian noise.
This claims to explain diffusion models from first principles, but the issue with explaining how they work is we don't know how they work. The explanation in the original paper turns out not to be true; you can get rid of most of their assumptions and it still works: https://arxiv.org/abs/2208.09392
I think it might be this paper [1] succintly described by the author in this twitter thread [2] [1] https://arxiv.org/abs/2208.09392 [2] https://twitter.com/tomgoldsteincs/status/156250381442263040...
More from the same topics.
Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan +11
Artificial intelligence (AI) researchers have been developing and refining large language models (LLMs) that exhibit remarkable capabilities across a variety of domains and tasks, challenging our understanding of learning and cognition.
Tom B. Brown, Benjamin Mann, Nick Ryder +28
Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-training on a large corpus of text followed by fine-tuning on a specific task.
Chiyuan Zhang, Samy Bengio, Moritz Hardt +2
Despite their massive size, successful deep artificial neural networks can exhibit a remarkably small difference between training and test performance.
A. Pluchino. A. E. Biondo, A. Rapisarda
The largely dominant meritocratic paradigm of highly competitive Western cultures is rooted on the belief that success is due mainly, if not exclusively, to personal qualities such as talent, intelligence, skills, efforts or risk taking.