Probabilistic Discriminative Learning with Layered Graphical Models

01/31/2019
by   Yuesong Shen, et al.
0

Probabilistic graphical models are traditionally known for their successes in generative modeling. In this work, we advocate layered graphical models (LGMs) for probabilistic discriminative learning. To this end, we design LGMs in close analogy to neural networks (NNs), that is, they have deep hierarchical structures and convolutional or local connections between layers. Equipped with tensorized truncated variational inference, our LGMs can be efficiently trained via backpropagation on mainstream deep learning frameworks such as PyTorch. To deal with continuous valued inputs, we use a simple yet effective soft-clamping strategy for efficient inference. Through extensive experiments on image classification over MNIST and FashionMNIST datasets, we demonstrate that LGMs are capable of achieving competitive results comparable to NNs of similar architectures, while preserving transparent probabilistic modeling.

READ FULL TEXT

page 5

page 8

research
03/20/2016

Composing graphical models with neural networks for structured representations and fast inference

We propose a general modeling and inference framework that composes prob...
research
03/08/2016

Discriminative models for robust image classification

A variety of real-world tasks involve the classification of images into ...
research
02/16/2019

Deep Convolutional Sum-Product Networks for Probabilistic Image Representations

Sum-Product Networks (SPNs) are hierarchical probabilistic graphical mod...
research
05/01/2018

On the Equivalence of Generative and Discriminative Formulations of the Sequential Dependence Model

The sequential dependence model (SDM) is a popular retrieval model which...
research
08/25/2019

Tutorial and Survey on Probabilistic Graphical Model and Variational Inference in Deep Reinforcement Learning

Probabilistic Graphical Modeling and Variational Inference play an impor...
research
11/15/2016

Unsupervised Learning with Truncated Gaussian Graphical Models

Gaussian graphical models (GGMs) are widely used for statistical modelin...
research
03/16/2018

Learning Sparse Deep Feedforward Networks via Tree Skeleton Expansion

Despite the popularity of deep learning, structure learning for deep mod...

Please sign up or login with your details

Forgot password? Click here to reset