274 citations · 3.1k across the 75 of their papers we have counts for
8 papers · 1 filter
Beyond Lazy Training for Over-parameterized Tensor Decomposition
Xiang Wang, Chenwei Wu, Jason D. Lee +2
Over-parametrization is an important technique in training neural networks. In both theory and practice, training a larger network allows the optimization algorithm to avoid bad lo…
Dissecting Hessian: Understanding Common Structure of Hessian in Neural Networks
Yikai Wu, Xingyu Zhu, Chenwei Wu +2
Hessian captures important properties of the deep neural network loss landscape. Previous works have observed low rank structure in the Hessians of neural networks. In this paper,…
Efficient sampling from the Bingham distribution
Rong Ge, Holden Lee, Jianfeng Lu +1
We give a algorithm for exact sampling from the Bingham distribution on the sphere with expected runtime of $\operatorname{poly}(d…
Optimization Landscape of Tucker Decomposition
Abraham Frandsen, Rong Ge
Tucker decomposition is a popular technique for many data analysis and machine learning applications. Finding a Tucker decomposition is a nonconvex optimization problem. As the sca…
Extracting Latent State Representations with Linear Dynamics from Rich Observations
Abraham Frandsen, Rong Ge
Recently, many reinforcement learning techniques were shown to have provable guarantees in the simple case of linear dynamics, especially in problems like linear quadratic regulato…
Guarantees for Tuning the Step Size using a Learning-to-Learn Approach
Xiang Wang, Shuai Yuan, Chenwei Wu +1
Choosing the right parameters for optimization algorithms is often the key to their success in practice. Solving this problem using a learning-to-learn approach -- using meta-gradi…