A normalizing flow models a complex probability density as an invertible transformation of a simple base density. Flows based on either coupling or autoregressive transforms both offer exact density evaluation and sampling, but rely on the parameterization of an easily invertible elementwise transformation, whose choice determines the flexibility of these models. Building upon recent work, we propose a fully-differentiable module based on monotonic rational-quadratic splines, which enhances the flexibility of both coupling and autoregressive transforms while retaining analytic invertibility. We demonstrate that neural spline flows improve density estimation, variational inference, and generative modeling of images.
|Title of host publication||Advances in Neural Information Processing Systems 32 (NeurIPS 2019)|
|Publisher||Neural Information Processing Systems Foundation, Inc|
|Number of pages||12|
|Publication status||Published - 14 Dec 2019|
|Event||33rd Conference on Neural Information Processing Systems - Vancouver Convention Centre, Vancouver, Canada|
Duration: 8 Dec 2019 → 14 Dec 2019
|Name||Advances in Neural Information Processing Systems|
|Conference||33rd Conference on Neural Information Processing Systems|
|Abbreviated title||NeurIPS 2019|
|Period||8/12/19 → 14/12/19|
FingerprintDive into the research topics of 'Neural Spline Flows'. Together they form a unique fingerprint.
- School of Informatics - Personal Chair of Machine Learning and Inference
- Institute for Adaptive and Neural Computation
- Data Science and Artificial Intelligence
Person: Academic: Research Active