mlsanityData to 7 Oct 2026

Langevin algorithms for Markovian Neural Networks and Deep Stochastic control

arXiv 2212.12018 ↗First posted 22 Dec 2022q-fin.CP cs.LG math.OCcited by 2

Not on the map. Why?

Abstract (arXiv)

Stochastic Gradient Descent Langevin Dynamics (SGLD) algorithms, which add noise to the classic gradient descent, are known to improve the training of neural networks in some cases where the neural network is very deep. In this paper we study the possibilities of training acceleration for the numerical resolution of stochastic control problems through gradient descent, where the control is parametrized by a neural network. If the control is applied at many discretization times then solving the stochastic control problem reduces to minimizing the loss of a very deep neural network. We numerically show that Langevin algorithms improve the training on various stochastic control problems like hedging and resource management, and for different choices of gradient descent methods.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 18 of its 34 references that are in the map. First posted on arXiv 22 Dec 2022.

Builds on

18 of 34 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2016Densely Connected Convolutional Networkscited by 6,691
  4. 2014Identifying and attacking the saddle point problem in high-dimensional non-convex optimizationcited by 286
  5. 2015Adding Gradient Noise Improves Learning for Very Deep Networkscited by 144
  6. 2015Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networkscited by 121
  7. 2018Deep Hedgingcited by 106
  8. 2018Which Neural Net Architectures Give Rise To Exploding and Vanishing Gradients?cited by 94
  9. 2016Noisy Activation Functionscited by 53
  10. 2016Deep Learning Approximation for Stochastic Control Problemscited by 51
  11. 2015Equilibrated adaptive learning rates for non-convex optimizationcited by 42
  12. 2019Convergence Analysis of Machine Learning Algorithms for the Numerical Solution of Mean Field Control and Games: II -- The Finite Horizon Casecited by 34
6 more
  1. 2018Deep neural networks algorithms for stochastic control problems on finite horizon: convergence analysiscited by 22
  2. 2018Deep neural networks algorithms for stochastic control problems on finite horizon: numerical applicationscited by 15
  3. 2019ProbAct: A Probabilistic Activation Function for Deep Neural Networkscited by 12
  4. 2019Deep Forward-Backward SDEs for Min-max Controlcited by 6
  5. 2019Adaptively Preconditioned Stochastic Gradient Langevin Dynamicscited by 5
  6. 2021Performance of a Markovian neural network versus dynamic programming on a fishing control problemcited by 2

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Anchored Langevin Algorithmscited by 2
  2. 2025Fokker-Planck to Callan-Symanzik: evolution of weight matrices under trainingcited by 0