Misha Belkin

Publication Activity (10 Years)

Years Active: 2005-2023
Publications (10 Years): 6

Top Topics

Directed Acyclic Graph

Learning Models

Top Venues

Publications

Arindam Banerjee, Pedro Cisneros-Velarde, Libin Zhu, Misha Belkin
Restricted Strong Convexity of Deep Learning Models with Smooth Activations. ICLR (2023)
Chaoyue Liu, Dmitriy Drusvyatskiy, Misha Belkin, Damek Davis, Yi-An Ma
Aiming towards the minimizers: fast convergence of SGD for overparametrized problems. NeurIPS (2023)
Yuan Cao, Zixiang Chen, Misha Belkin, Quanquan Gu
Benign Overfitting in Two-layer Convolutional Neural Networks. NeurIPS (2022)
Chaoyue Liu, Libin Zhu, Misha Belkin
Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models. ICLR (2022)
Neil Mallinar, James B. Simon, Amirhesam Abedsoltan, Parthe Pandit, Misha Belkin, Preetum Nakkiran
Benign, Tempered, or Catastrophic: Toward a Refined Taxonomy of Overfitting. NeurIPS (2022)
Libin Zhu, Chaoyue Liu, Misha Belkin
Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture. NeurIPS (2022)
Misha Belkin, Partha Niyogi, Vikas Sindhwani
On Manifold Regularization. AISTATS (2005)