Fetching the paper…

Reading the bibliography…

2020

SoftFlow: Probabilistic Framework for Normalizing Flow on Manifolds

Kim, Hyeongju, Lee, Hyeonseung, Kang, Woo Hyun et al.

Original
PDF
Post on X

Understand

Flow-based generative models are composed of invertible transformations between two random variables of the same dimension.

Therefore, flow-based models cannot be adequately trained if the dimension of the data distribution does not match that of the underlying target distribution.
In this paper, we propose SoftFlow, a probabilistic framework for training normalizing flows on manifolds.
To sidestep the dimension mismatch problem, SoftFlow estimates a conditional distribution of the perturbed input data instead of learning the data distribution directly.

SoftFlow: Probabilistic Framework for Normalizing Flow on Manifolds · Around

Built on

A stochastic estimator of the trace of the influence matrix for laplacian smoothing splines
Hutchinson, M. F · 1990
Earlier work this paper cites.
The change-of-variables formula using matrix volume
Ben-Israel, A · 1999
Earlier work this paper cites.
Auto-encoding variational bayes
Original
Kingma, D. P. and Welling, M · 2013
Earlier work this paper cites.
Nice: Non-linear independent components estimation
Original
Dinh, L., Krueger, D., and Bengio, Y · 2014
Earlier work this paper cites.
Adam: A method for stochastic optimization
Original
Kingma, D. P. and Ba, J · 2014
Earlier work this paper cites.
Shapenet: An information-rich 3d model repository
Original
Chang, A. X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., Su, H., et al · 2015
Earlier work this paper cites.
Variational inference with normalizing flows
Original
Rezende, D. J. and Mohamed, S · 2015
Earlier work this paper cites.
Density estimation using real nvp
Original
Dinh, L., Sohl-Dickstein, J., and Bengio, S · 2016
Earlier work this paper cites.
Normalizing flows on riemannian manifolds
Original
Gemici, M. C., Rezende, D., and Mohamed, S · 2016
Earlier work this paper cites.

Similar

Revisiting classifier two-sample tests
Original
Lopez-Paz, D. and Oquab, M · 2016
Cited alongside, same era.
Learning representations and generative models for 3d point clouds
Original
Achlioptas, P., Diamanti, O., Mitliagkas, I., and Guibas, L · 2017
Cited alongside, same era.
Masked autoregressive flow for density estimation
Papamakarios, G., Pavlakou, T., and Murray, I · 2017
Cited alongside, same era.
Neural ordinary differential equations
Chen, T. Q., Rubanova, Y., Bettencourt, J., and Duvenaud, D. K · 2018
Cited alongside, same era.
Ffjord: Free-form continuous dynamics for scalable reversible generative models
Original
Grathwohl, W., Chen, R. T., Bettencourt, J., Sutskever, I., and Duvenaud, D · 2018
Cited alongside, same era.

Then

Augmented neural odes
Dupont, E., Doucet, A., and Teh, Y. W · 2019
Later among the works it cites.
Flow++: Improving flow-based generative models with variational dequantization and architecture design
Original
Ho, J., Chen, X., Srinivas, A., Duan, Y., and Abbeel, P · 2019
Later among the works it cites.
Videoflow: A flow-based generative model for video
Original
Kumar, M., Babaeizadeh, M., Erhan, D., Finn, C., Levine, S., Dinh, L., and Kingma, D · 2019
Later among the works it cites.
Flowseq: Non-autoregressive conditional sequence generation with generative flow
Original
Ma, X., Zhou, C., Li, X., Neubig, G., and Hovy, E · 2019
Later among the works it cites.
Waveglow: A flow-based generative network for speech synthesis
Prenger, R., Valle, R., and Catanzaro, B · 2019
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

A papier-mâché approach to learning 3d surface generation

Groueix, T., Fisher, M., Kim, V. G., Russell, B. C., and Aubry, M · 2018

Cited alongside, same era.

Flowavenet: A generative flow for raw audio

Kim, S., Lee, S.-g., Song, J., Kim, J., and Yoon, S · 2018

Cited alongside, same era.

Glow: Generative flow with invertible 1x1 convolutions

Kingma, D. P. and Dhariwal, P · 2018

Cited alongside, same era.

Point cloud gan

Original

Li, C.-L., Zaheer, M., Zhang, Y., Poczos, B., and Salakhutdinov, R · 2018

Cited alongside, same era.

Blow: a single-scale hyperconditioned flow for non-parallel raw-audio voice conversion

Serrà, J., Pascual, S., and Perales, C. S · 2019

Later among the works it cites.

Pointflow: 3d point cloud generation with continuous normalizing flows

Yang, G., Huang, X., Hao, Z., Liu, M.-Y., Belongie, S., and Hariharan, B · 2019

Later among the works it cites.

Flows for simultaneous manifold learning and density estimation

Brehmer, J. and Cranmer, K · 2020

Closest in time.

Normalizing flows on tori and spheres

Rezende, D. J., Papamakarios, G., Racanière, S., Albergo, M. S., Kanwar, G., Shanahan, P. E., and Cranmer, K · 2020

Closest in time.