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
  • [21] Local Identifiability of Deep ReLU Neural Networks: the Theory
    Bona-Pellissier, Joachim
    Malgouyres, Francois
    Bachoc, Francois
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [22] Stochastic Stability of Delayed Neural Networks With Local Impulsive Effects
    Zhang, Wenbing
    Tang, Yang
    Wong, Wai Keung
    Miao, Qingying
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2015, 26 (10) : 2336 - 2345
  • [23] Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks
    Li, Chunyuan
    Chen, Changyou
    Carlson, David
    Carin, Lawrence
    THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2016, : 1788 - 1794
  • [24] Stochastic perturbation of subgradient algorithm for nonconvex deep neural networks
    A. El Mouatasim
    J. E. Souza de Cursi
    R. Ellaia
    Computational and Applied Mathematics, 2023, 42
  • [25] Stochastic Layer-Wise Precision in Deep Neural Networks
    Lacey, Griffin
    Taylor, Graham W.
    Areibi, Shawki
    UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, 2018, : 663 - 672
  • [26] Stochastic perturbation of subgradient algorithm for nonconvex deep neural networks
    El Mouatasim, A.
    de Cursi, J. E. Souza
    Ellaia, R.
    COMPUTATIONAL & APPLIED MATHEMATICS, 2023, 42 (04):
  • [27] Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations
    Xu, Winnie
    Chen, Ricky T. Q.
    Li, Xuechen
    Duvenaud, David
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 151, 2022, 151 : 721 - 738
  • [28] Regularizing Deep Neural Networks with Stochastic Estimators of Hessian Trace
    Liu, Yucong
    Yu, Shixing
    Lin, Tong
    arXiv, 2022,
  • [29] ASYNCHRONOUS STOCHASTIC OPTIMIZATION FOR SEQUENCE TRAINING OF DEEP NEURAL NETWORKS
    Heigold, Georg
    McDermott, Erik
    Vanhoucke, Vincent
    Senior, Andrew
    Bacchiani, Michiel
    2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,
  • [30] Exploiting Correlation in Stochastic Computing based Deep Neural Networks
    Frasser, Christiam F.
    Linares-Serrano, Pablo
    Moran, Alejandro
    Font-Rossello, Joan
    Canals, V
    Roca, Miquel
    Serrano-Gotarredona, T.
    Rossello, Josep L.
    2021 XXXVI CONFERENCE ON DESIGN OF CIRCUITS AND INTEGRATED SYSTEMS (DCIS21), 2021, : 113 - 118
12345