Timezone: »
Scaling Graphically Structured Diffusion Models
Christian Weilbach · William Harvey · Hamed Shirzad · Frank Wood
Event URL: https://openreview.net/forum?id=pzH65nCyCN »
Applications of the recently introduced graphically structured diffusion model (GSDM) family show that sparsifying the transformer attention mechanism within a diffusion model and meta-training on a variety of conditioning tasks can yield an efficiently learnable diffusion model artifact that is capable of flexible, in the sense of observing different subsets of variables at test-time, amortized conditioning in probabilistic graphical models. While extremely promising in terms of applicability and utility, implementations of GSDMs prior to this work were not scalable beyond toy graphical model sizes. We overcome this limitation by describing and and solving two scaling issues related to GSDMs; one engineering and one methodological. We additionally propose a new benchmark problem of weight inference for a convolutional neural network applied to $14\times14$ MNIST.
Applications of the recently introduced graphically structured diffusion model (GSDM) family show that sparsifying the transformer attention mechanism within a diffusion model and meta-training on a variety of conditioning tasks can yield an efficiently learnable diffusion model artifact that is capable of flexible, in the sense of observing different subsets of variables at test-time, amortized conditioning in probabilistic graphical models. While extremely promising in terms of applicability and utility, implementations of GSDMs prior to this work were not scalable beyond toy graphical model sizes. We overcome this limitation by describing and and solving two scaling issues related to GSDMs; one engineering and one methodological. We additionally propose a new benchmark problem of weight inference for a convolutional neural network applied to $14\times14$ MNIST.
Author Information
Christian Weilbach (Department of Computer Science, University of British Columbia)
William Harvey (University of British Columbia)
Hamed Shirzad (University of British Columbia)
Frank Wood (UBC + inverted.ai)
More from the Same Authors
-
2023 : Visual Chain-of-Thought Diffusion Models »
William Harvey · Frank Wood -
2023 Oral: Uncertain Evidence in Probabilistic Models and Stochastic Simulators »
Andreas Munk · Alexander Mead · Frank Wood -
2023 Poster: Graphically Structured Diffusion Models »
Christian Weilbach · William Harvey · Frank Wood -
2023 Poster: Exphormer: Sparse Transformers for Graphs »
Hamed Shirzad · Ameya Velingker · Balaji Venkatachalam · Danica J Sutherland · Ali K Sinop -
2023 Oral: Graphically Structured Diffusion Models »
Christian Weilbach · William Harvey · Frank Wood -
2023 Poster: Uncertain Evidence in Probabilistic Models and Stochastic Simulators »
Andreas Munk · Alexander Mead · Frank Wood -
2021 Poster: Robust Asymmetric Learning in POMDPs »
Andrew Warrington · Jonathan Lavington · Adam Scibior · Mark Schmidt · Frank Wood -
2021 Oral: Robust Asymmetric Learning in POMDPs »
Andrew Warrington · Jonathan Lavington · Adam Scibior · Mark Schmidt · Frank Wood -
2020 Poster: All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference »
Rob Brekelmans · Vaden Masrani · Frank Wood · Greg Ver Steeg · Aram Galstyan -
2019 Poster: Amortized Monte Carlo Integration »
Adam Golinski · Frank Wood · Tom Rainforth -
2019 Oral: Amortized Monte Carlo Integration »
Adam Golinski · Frank Wood · Tom Rainforth -
2018 Poster: Deep Variational Reinforcement Learning for POMDPs »
Maximilian Igl · Luisa Zintgraf · Tuan Anh Le · Frank Wood · Shimon Whiteson -
2018 Oral: Deep Variational Reinforcement Learning for POMDPs »
Maximilian Igl · Luisa Zintgraf · Tuan Anh Le · Frank Wood · Shimon Whiteson