Maximum Entropy Flow Networks
arXiv:1701.03504
Abstract
Maximum entropy modeling is a flexible and popular framework for formulating statistical models given partial knowledge. In this paper, rather than the traditional method of optimizing over the continuous density directly, we learn a smooth and invertible transformation that maps a simple distribution to the desired maximum entropy distribution. Doing so is nontrivial in that the objective being maximized (entropy) is a function of the density itself. By exploiting recent developments in normalizing flow networks, we cast the maximum entropy problem into a finite-dimensional constrained optimization, and solve the problem by combining stochastic optimization with the augmented Lagrangian method. Simulation results demonstrate the effectiveness of our method, and applications to finance and computer vision show the flexibility and accuracy of using maximum entropy flow networks.
arXiv commentAccepted at ICLR 2017
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- ADADELTA: An Adaptive Learning Rate Method
- Density estimation using Real NVP
- Texture Synthesis Using Convolutional Neural Networks
- Learning in Implicit Generative Models
- On the Expressive Power of Deep Neural Networks
- On the Convergence of Bound Optimization Algorithms