Variants of RMSProp and Adagrad with Logarithmic Regret Bounds MC Mukkamala, M Hein ICML 2017, 2017 | 141 | 2017 |
On the loss landscape of a class of deep neural networks with no bad local valleys Q Nguyen, MC Mukkamala, M Hein ICLR 2019, 2019 | 43 | 2019 |
Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions Q Nguyen, MC Mukkamala, M Hein ICML 2018, 2018 | 24 | 2018 |
Convex-Concave backtracking for inertial Bregman proximal gradient algorithms in nonconvex optimization MC Mukkamala, P Ochs, T Pock, S Sabach SIAM Journal on Mathematics of Data Science 2 (3), 658-682, 2020 | 14 | 2020 |
Beyond Alternating Updates for Matrix Factorization with Inertial Bregman Proximal Gradient Algorithms MC Mukkamala, P Ochs NeurIPS 2019, 2019 | 8 | 2019 |
Bregman proximal framework for deep linear neural networks MC Mukkamala, F Westerkamp, E Laude, D Cremers, P Ochs arXiv preprint arXiv:1910.03638, 2019 | 2 | 2019 |
Global Convergence of Model Function Based Bregman Proximal Minimization Algorithms MC Mukkamala, J Fadili, P Ochs arXiv preprint arXiv:2012.13161, 2020 | | 2020 |