On Local Entropy, Stochastic Control, and Deep Neural Networks

被引：2
|
作者：
Pavon, Michele [1 ]
机构：
[1] Univ Padua, Dipartimento Matemat, I-35122 Padua, Italy
来源：
IEEE CONTROL SYSTEMS LETTERS | 2023年 / 7卷
关键词：
Entropy; Stochastic processes; Q measurement; Bridges; Volume measurement; Neural networks; Particle measurements; Stochastic optimal control; machine learning; neural networks; OPTIMAL TRANSPORT; REVERSAL;
D O I：
10.1109/LCSYS.2022.3189927
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In this letter, we connect some recent papers on smoothing of energy landscapes and scored-based generative models of machine learning to classical work in stochastic control. We clarify these connections providing rigorous statements and representations which may serve as guidelines for further learning models.
引用
收藏
页码：437 / 441
页数：5
相关论文
共 50 条
  • [1] Minimum entropy control for stochastic systems based on the wavelet neural networks
    Yang, Chengzhi
    ADVANCES IN NEURAL NETWORKS - ISNN 2006, PT 2, PROCEEDINGS, 2006, 3972 : 968 - 974
  • [2] Langevin Algorithms for Markovian Neural Networks and Deep Stochastic Control
    Bras, Pierre
    Pages, Gilles
    2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,
  • [3] Transfer Entropy in Deep Neural Networks
    Andonie, R.
    Cataron, A.
    Moldovan, A.
    INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL, 2025, 20 (01)
  • [4] Convergence of stochastic gradient descent under a local Lojasiewicz condition for deep neural networks
    An, Jing
    Lu, Jianfeng
    arXiv, 2023,
  • [5] A New Stochastic Mutiplier for Deep Neural Networks
    Huh, Subin
    Yu, Joonsang
    Choi, Kiyoung
    PROCEEDINGS INTERNATIONAL SOC DESIGN CONFERENCE 2017 (ISOCC 2017), 2017, : 46 - 47
  • [6] Entropy-Constrained Training of Deep Neural Networks
    Wiedemann, Simon
    Marban, Arturo
    Mueller, Klaus-Robert
    Samek, Wojciech
    2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2019,
  • [7] Entropy and mutual information in models of deep neural networks
    Gabrie, Marylou
    Manoel, Andre
    Luneau, Clement
    Barbier, Jean
    Macris, Nicolas
    Krzakala, Florent
    Zdeborova, Lenka
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
  • [8] Entropy and mutual information in models of deep neural networks
    Gabrie, Marylou
    Manoel, Andre
    Luneau, Clement
    Barbier, Jean
    Macris, Nicolas
    Krzakala, Florent
    Zdeborova, Lenka
    JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT, 2019, 2019 (12):
  • [9] Deep Neural Networks Algorithms for Stochastic Control Problems on Finite Horizon: Numerical Applications
    Achref Bachouch
    Côme Huré
    Nicolas Langrené
    Huyên Pham
    Methodology and Computing in Applied Probability, 2022, 24 : 143 - 178
  • [10] Deep Neural Networks Algorithms for Stochastic Control Problems on Finite Horizon: Numerical Applications
    Bachouch, Achref
    Hure, Come
    Langrene, Nicolas
    Huyen Pham
    METHODOLOGY AND COMPUTING IN APPLIED PROBABILITY, 2022, 24 (01) : 143 - 178
12345