paper-with-me

Papers

Why Do Local Methods Solve Nonconvex Problems?

2021-03-24 · Tengyu Ma

Non-convex optimization is ubiquitous in modern machine learning. Researchers devise non-convex objective functions and optimize them using off-the-shelf optimizers such as stochastic gradient descent and its variants, which leverage the local geometry and update iteratively. Even though solving non-convex functions is NP-hard in the worst case, the optimization quality in practice is often not an issue -- optimizers are largely believed to find approximate global minima. Researchers hypothesize a unified explanation for this intriguing phenomenon: most of the local minima of the practically-used objectives are approximately global minima. We rigorously formalize it for concrete instances of machine learning problems.

📄 PDF Abstract BibTeX arXiv:2103.13462

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine Learning

Similar Papers 제목 키워드 기반

Projective Proximal Gradient Descent for A Class of Nonconvex Nonsmooth Optimization Problems: Fast Convergence Without Kurdyka-Lojasiewicz (KL) Property

2023-04-20 · Yingzhen Yang, Ping Li

Nonconvex and nonsmooth optimization problems are important and challenging for statistics and machine learning. In this paper, we propose Projected Proximal Gradient Descent (PPGD) which solves a class of nonconvex and …

An efficient nonconvex reformulation of stagewise convex optimization problems

2020-10-27 · NeurIPS 2020 12 · Rudy Bunel, Oliver Hinder, Srinadh Bhojanapalli, Krishnamurthy 외

Convex optimization problems with staged structure appear in several contexts, including optimal control, verification of deep neural networks, and isotonic regression. Off-the-shelf solvers can solve these problems but …

Implementing Robust M-Estimators with Certifiable Factor Graph Optimization

2026-03-21 · Zhexin Xu, Hanna Jiamei Zhang, Helena Calatrava, Pau Closas 외 arxiv

Parameter estimation in robotics and computer vision faces formidable challenges from both outlier contamination and nonconvex optimization landscapes. While M-estimation addresses the problem of outliers through robust …

Recursive Decomposition for Nonconvex Optimization

2016-11-08 · Abram L. Friesen, Pedro Domingos

Continuous optimization is an important problem in many areas of AI, including vision, robotics, probabilistic inference, and machine learning. Unfortunately, most real-world optimization problems are nonconvex, causing …

Combinatorial Optimizationgraph partitioningProblem DecompositionProtein Folding

A Single-Loop Gradient Descent and Perturbed Ascent Algorithm for Nonconvex Functional Constrained Optimization

2022-07-12 · Songtao Lu

Nonconvex constrained optimization problems can be used to model a number of machine learning problems, such as multi-class Neyman-Pearson classification and constrained Markov decision processes. However, such kinds of …