Liang Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Liang Li has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
Zdzisław Brzeźniak
2 shared publicationsBen Goldys
1 shared publication- Erika Hausenblas
Department Mathematik und Informationstechnologie, Montanuniversität Leoben, Leoben, Austria
1 shared publication - Huiting Guo
College of Mathematics and Physics, Beijing University of Chemical Technology, Beijing, China
1 shared publication - Li Wang
College of Mathematics and Physics, Beijing University of Chemical Technology, Beijing, China
1 shared publication - Yongli Xu
Department of Mathematics, Beijing University of Chemical Technology, Beijing, China
1 shared publication
Latest Publications
- 23 June 2025
- Published by Springer Nature in Computational Economics
- Vol. 67 (6) , 4453-4476
Pricing Convertible Bonds Based on GAN and Transformer
- 23 June 2025
- Published by Springer Nature in Computational Economics
- Vol. 67 (6) , 4453-4476
Pricing Convertible Bonds Based on GAN and Transformer
- 14 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (3) , 5826-5832
Learning Rates of Deep Nets for Geometrically Strongly Mixing Sequence
The great success of deep learning poses an urgent challenge to establish the theoretical basis for its working mechanism. Recently, research on the convergence of deep neural networks (DNNs) has made great progress. However, the existing studies are based on the assumption that the samples are independent, which is too strong to be applied to many real-world scenarios. In this brief, we establish a fast learning rate for the empirical risk minimization (ERM) on DNN regression with dependent samples, and the dependence is expressed in terms of geometrically strongly mixing sequence. To the best of our knowledge, this is the first convergence result of DNN methods based on mixing sequences. This result is a natural generalization of the independent sample case.
- 14 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (3) , 5826-5832
Learning Rates of Deep Nets for Geometrically Strongly Mixing Sequence
The great success of deep learning poses an urgent challenge to establish the theoretical basis for its working mechanism. Recently, research on the convergence of deep neural networks (DNNs) has made great progress. However, the existing studies are based on the assumption that the samples are independent, which is too strong to be applied to many real-world scenarios. In this brief, we establish a fast learning rate for the empirical risk minimization (ERM) on DNN regression with dependent samples, and the dependence is expressed in terms of geometrically strongly mixing sequence. To the best of our knowledge, this is the first convergence result of DNN methods based on mixing sequences. This result is a natural generalization of the independent sample case.
- 1 February 2024
- Published by Elsevier in Journal of Differential Equations
- Vol. 390, 58-124
3D stochastic Landau-Lifshitz-Gilbert equations coupled with Maxwell's equations with full energy
- 1 February 2024
- Published by Elsevier in Journal of Differential Equations
- Vol. 390, 58-124
3D stochastic Landau-Lifshitz-Gilbert equations coupled with Maxwell's equations with full energy
- 1 August 2019
- Published by Elsevier in Journal of Differential Equations
- Vol. 267 (4) , 2284-2330
Quasipotential for the ferromagnetic wire governed by the 1D Landau-Lifshitz-Gilbert equations
- 1 August 2019
- Published by Elsevier in Journal of Differential Equations
- Vol. 267 (4) , 2284-2330
Quasipotential for the ferromagnetic wire governed by the 1D Landau-Lifshitz-Gilbert equations