Đỗ Minh Thắng

Liên hệ

Các công bố khoa học

Ấn phẩm

1. 1. Đỗ Minh Thắng, Sonja Hannibal, Arnulf Jentzen, Non-convergence to global minimizers in data driven supervised deep learning: Adam and stochastic gradient descent optimization provably fail to converge to global minimizers in the training of deep neural networks with ReLU activation, Journal of Mathematical Analysis and Applications, 564 (2026) 130724 (2026)
2. 2. Đỗ Minh Thắng, Ngô Hoàng Long, Dai Taguchi, Strong solution and approximation of time-dependent radial Dunkl processes with multiplicative noise, Journal of Computational and Applied Mathematics Volume 486, November 2026, 117655 (2026)
3. 3. Đỗ Minh Thắng, Ngô Hoàng Long, Phó Nhật An, Tamed-adaptive Euler-Maruyama approximation for SDEs with superlinearly growing and piecewise continuous drift, superlinearly growing and locally Hölder continuous diffusion, Journal of Complexity, Volume 82, June 2024, 101833 (2024)

Các hoạt động khoa học

Seminar

1. Non-Convergence and Convergence Rates of SGD methods in Deep Learning.