paper-with-me

홈 › Papers

Mutual Information Gradient Estimation for Representation Learning

2020-05-03 · ICLR 2020 1 · Liangjian Wen, Yiji Zhou, Lirong He, Mingyuan Zhou, Zenglin Xu

Mutual Information (MI) plays an important role in representation learning. However, MI is unfortunately intractable in continuous and high-dimensional settings. Recent advances establish tractable and scalable MI estimators to discover useful representation. However, most of the existing methods are not capable of providing an accurate estimation of MI with low-variance when the MI is large. We argue that directly estimating the gradients of MI is more appealing for representation learning than estimating MI in itself. To this end, we propose the Mutual Information Gradient Estimator (MIGE) for representation learning based on the score estimation of implicit distributions. MIGE exhibits a tight and smooth gradient estimation of MI in the high-dimensional and large-MI settings. We expand the applications of MIGE in both unsupervised learning of deep representations based on InfoMax and the Information Bottleneck method. Experimental results have indicated significant performance improvement in learning useful representation.

📄 PDF Abstract BibTeX arXiv:2005.01123

Code (1)

zhouyiji/MIGE pytorch

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

MINE: Mutual Information Neural Estimation

2018-01-12 · Mohamed Ishmael Belghazi, Aristide Baratin, Sai Rajeswar, Sherjil Ozair 외

We argue that the estimation of mutual information between high dimensional continuous random variables can be achieved by gradient descent over neural networks. We present a Mutual Information Neural Estimator (MINE) th…

General Classification

Mutual Information Neural Estimation

2018-07-01 · ICML 2018 7 · Mohamed Ishmael Belghazi, Aristide Baratin, Sai Rajeshwar, Sherjil Ozair 외

We argue that the estimation of mutual information between high dimensional continuous random variables can be achieved by gradient descent over neural networks. We present a Mutual Information Neural Estimator (MIN…

General ClassificationMutual Information Estimation

Generalized Bregman Divergence and Gradient of Mutual Information for Vector Poisson Channels

2013-01-28 · Liming Wang, Miguel Rodrigues, Lawrence Carin

We investigate connections between information-theoretic and estimation-theoretic quantities in vector Poisson channel models. In particular, we generalize the gradient of mutual information with respect to key system pa…

Compressive SensingDocument Classification

Matching Text with Deep Mutual Information Estimation

2020-03-09 · Xixi Zhou, Chengxi Li, Jiajun Bu, Chengwei Yao 외

Text matching is a core natural language processing research problem. How to retain sufficient information on both content and structure information is one important challenge. In this paper, we present a neural approach…

Answer SelectionMutual Information EstimationNatural Language InferenceParaphrase Identification+1

Neural Topic Modeling with Deep Mutual Information Estimation

2022-03-12 · Kang Xu, Xiaoqiu Lu, Yuan-Fang Li, Tongtong Wu 외

The emerging neural topic models make topic modeling more easily adaptable and extendable in unsupervised text mining. However, the existing neural topic models is difficult to retain representative information of the do…

Mutual Information EstimationText ClusteringTopic Models