Perturbed Proximal Descent to Escape Saddle Points for Non-convex and Non-smooth Objective Functions
arXiv:1901.08958 · doi:10.1007/978-3-030-16841-4_7
Abstract
We consider the problem of finding local minimizers in non-convex and non-smooth optimization. Under the assumption of strict saddle points, positive results have been derived for first-order methods. We present the first known results for the non-smooth case, which requires different analysis and a different algorithm.
arXiv commentarXiv admin note: text overlap with arXiv:1703.00887 by other authors
References in corpus (5)
- Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
- How to Escape Saddle Points Efficiently
- Forward-backward quasi-Newton methods for nonsmooth optimization problems
- Neon2: Finding Local Minima via First-Order Oracles
- Gradient Descent Can Take Exponential Time to Escape Saddle Points
Cited by in corpus (4)
- Single-pass Object-adaptive Data Undersampling and Reconstruction for MRI
- General Low-rank Matrix Optimization: Geometric Analysis and Sharper Bounds
- Escaping Saddle Points for Nonsmooth Weakly Convex Functions via Perturbed Proximal Algorithms
- Stochastic Gradient Langevin Dynamics with Variance Reduction