A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning

Author:

Huijben Iris A. M.1ORCID,Kool Wouter2ORCID,Paulus Max B.3,van Sloun Ruud J. G.1ORCID

Affiliation:

1. Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands

2. Amsterdam Machine Learning Lab (AMLab), University of Amsterdam, Amsterdam, The Netherlands

3. Department of Computer Science, ETH, Zürich, Switzerland

Funder

Onera Health and the Project

European Regional Development Fund

ORTEC

Max Planck ETH Center for Learning Systems

Sustainable Chemical Processes through Catalysis

National Center of Competence in Research

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Applied Mathematics,Artificial Intelligence,Computational Theory and Mathematics,Computer Vision and Pattern Recognition,Software

Reference171 articles.

1. Neural Machine Translation with Gumbel-Greedy Decoding

2. Best of both worlds: Transferring knowledge from discriminative learning to a generative visual dialog model;lu;Proc Conf Neural Informat Process Syst,2017

3. Making Use of Latent Space in Language GANs for Generating Diverse Text without Pre-training

4. Relgan: Relational generative adversarial networks for text generation;nie;Proc Int Conf Learn Representations,2019

5. GANS for sequences of discrete elements with the gumbel-softmax distribution;kusner,2016

Cited by 23 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Neural quantile optimization for edge–cloud networking;Computer Networks;2024-11

2. Complete synchronization of delayed discrete-time fractional-order competitive neural networks;Applied Mathematics and Computation;2024-10

3. Conditional computation in neural networks: Principles and research trends;Intelligenza Artificiale;2024-07-31

4. Neural Click Models for Recommender Systems;Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval;2024-07-10

5. Adversarial Pairwise Multimodal Recommendation;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3