5 papers
A Gaussian smoothing-based zeroth-order method for Goldstein second-order stationarity
Ming Lei, Ting Kei Pong, Man-Chung Yue +2
We introduce a new generalized Hessian, called the Goldstein second-order -subdifferential, and an associated notion of -second-order stationary point for conti…
Burer-Monteiro factorizability of nuclear norm regularized optimization
Wenqing Ouyang, Ting Kei Pong, Man-Chung Yue
This paper studies the relationship between the nuclear norm-regularized minimization problem, which minimizes the sum of a function and a positive multiple of the nuclea…
Anchored Spectral Estimator for Rigid Motion Synchronization
Ziyue Zhao, Huikang Liu, Man-Chung Yue
A rigid motion in consists of a proper rotation and a translation, and it can be represented as a matrix in . The problem of rigid mo…
An error bound-based convergence analysis framework for a class of randomized algorithms
Zhichun Yang, Li Jiang, Tianxiang Liu +1
Existing error-bound-based analyses for stochastic algorithms that exhibit certain descent properties, such as randomized coordinate descent and randomized projection methods, are…
Subdifferentially polynomially bounded functions and Gaussian smoothing-based zeroth-order optimization
Ming Lei, Ting Kei Pong, Shuqin Sun +1
We study the class of subdifferentially polynomially bounded (SPB) functions, which is a rich class of locally Lipschitz functions that encompasses all Lipschitz functions, all gra…