Timezone: »
Normalizing flows are generative models that provide tractable density estimation via an invertible transformation from a simple base distribution to a complex target distribution. However, this technique cannot directly model data supported on an unknown low-dimensional manifold, a common occurrence in real-world domains such as image data. Recent attempts to remedy this limitation have introduced geometric complications that defeat a central benefit of normalizing flows: exact density estimation. We recover this benefit with Conformal Embedding Flows, a framework for designing flows that learn manifolds with tractable densities. We argue that composing a standard flow with a trainable conformal embedding is the most natural way to model manifold-supported data. To this end, we present a series of conformal building blocks and apply them in experiments with synthetic and real-world data to demonstrate that flows can model manifold-supported distributions without sacrificing tractable likelihoods.
Author Information
Brendan Ross (Layer 6 AI)
Jesse Cresswell (Layer 6 AI)
More from the Same Authors
-
2022 : CaloMan: Fast generation of calorimeter showers with density estimation on learned manifolds »
Jesse Cresswell · Brendan Ross · Gabriel Loaiza-Ganem · Humberto Reyes-Gonzalez · Marco Letizia · Anthony Caterini -
2022 : Find Your Friends: Personalized Federated Learning with the Right Collaborators »
Yi Sui · Junfeng Wen · Yenson Lau · Brendan Ross · Jesse Cresswell -
2022 : The Union of Manifolds Hypothesis »
Bradley Brown · Anthony Caterini · Brendan Ross · Jesse Cresswell · Gabriel Loaiza-Ganem -
2022 : Denoising Deep Generative Models »
Gabriel Loaiza-Ganem · Brendan Ross · Luhuan Wu · John Cunningham · Jesse Cresswell · Anthony Caterini -
2023 Poster: Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models »
George Stein · Jesse Cresswell · Rasa Hosseinzadeh · Yi Sui · Brendan Ross · Valentin Villecroze · Zhaoyan Liu · Anthony Caterini · Eric Taylor · Gabriel Loaiza-Ganem -
2022 : Disparate Impact in Differential Privacy from Gradient Misalignment »
Maria Esipova · Atiyeh Ashari · Yaqiao Luo · Jesse Cresswell