Skip to main content

On fenchel mini-max learning

Publication ,  Conference
Tao, C; Chen, L; Dai, S; Chen, J; Bai, K; Wang, D; Feng, J; Lu, W; Bobashev, G; Carin, L
Published in: Advances in Neural Information Processing Systems
January 1, 2019

Inference, estimation, sampling and likelihood evaluation are four primary goals of probabilistic modeling. Practical considerations often force modeling approaches to make compromises between these objectives. We present a novel probabilistic learning framework, called Fenchel Mini-Max Learning (FML), that accommodates all four desiderata in a flexible and scalable manner. Our derivation is rooted in classical maximum likelihood estimation, and it overcomes a longstanding challenge that prevents unbiased estimation of unnormalized statistical models. By reformulating MLE as a mini-max game, FML enjoys an unbiased training objective that (i) does not explicitly involve the intractable normalizing constant and (ii) is directly amendable to stochastic gradient descent optimization. To demonstrate the utility of the proposed approach, we consider learning unnormalized statistical models, nonparametric density estimation and training generative models, with encouraging empirical results presented.

Duke Scholars

Published In

Advances in Neural Information Processing Systems

ISSN

1049-5258

Publication Date

January 1, 2019

Volume

32

Related Subject Headings

  • 4611 Machine learning
  • 1702 Cognitive Sciences
  • 1701 Psychology
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Tao, C., Chen, L., Dai, S., Chen, J., Bai, K., Wang, D., … Carin, L. (2019). On fenchel mini-max learning. In Advances in Neural Information Processing Systems (Vol. 32).
Tao, C., L. Chen, S. Dai, J. Chen, K. Bai, D. Wang, J. Feng, W. Lu, G. Bobashev, and L. Carin. “On fenchel mini-max learning.” In Advances in Neural Information Processing Systems, Vol. 32, 2019.
Tao C, Chen L, Dai S, Chen J, Bai K, Wang D, et al. On fenchel mini-max learning. In: Advances in Neural Information Processing Systems. 2019.
Tao, C., et al. “On fenchel mini-max learning.” Advances in Neural Information Processing Systems, vol. 32, 2019.
Tao C, Chen L, Dai S, Chen J, Bai K, Wang D, Feng J, Lu W, Bobashev G, Carin L. On fenchel mini-max learning. Advances in Neural Information Processing Systems. 2019.

Published In

Advances in Neural Information Processing Systems

ISSN

1049-5258

Publication Date

January 1, 2019

Volume

32

Related Subject Headings

  • 4611 Machine learning
  • 1702 Cognitive Sciences
  • 1701 Psychology