Threshold activation functions are highly preferable in neural networks ...
In second-order optimization, a potential bottleneck can be computing th...
We propose a randomized algorithm with quadratic convergence rate for co...
We consider least-squares problems with quadratic regularization and pro...
We propose novel randomized optimization methods for high-dimensional co...
We are interested in two-layer ReLU neural networks from an optimization...
We propose a new randomized algorithm for solving L2-regularized
least-s...
We provide an exact analysis of a class of randomized algorithms for sol...
We provide an exact analysis of the limiting spectrum of matrices random...
We investigate randomized methods for solving overdetermined linear
leas...
We propose a new randomized optimization method for high-dimensional pro...
We study risk-sensitive imitation learning where the agent's goal is to
...
The literature on Inverse Reinforcement Learning (IRL) typically assumes...