{"title":"函数约束算法解决凸简单双层问题","authors":"Huaqing Zhang, Lesi Chen, Jing Xu, Jingzhao Zhang","doi":"arxiv-2409.06530","DOIUrl":null,"url":null,"abstract":"This paper studies simple bilevel problems, where a convex upper-level\nfunction is minimized over the optimal solutions of a convex lower-level\nproblem. We first show the fundamental difficulty of simple bilevel problems,\nthat the approximate optimal value of such problems is not obtainable by\nfirst-order zero-respecting algorithms. Then we follow recent works to pursue\nthe weak approximate solutions. For this goal, we propose novel near-optimal\nmethods for smooth and nonsmooth problems by reformulating them into\nfunctionally constrained problems.","PeriodicalId":501340,"journal":{"name":"arXiv - STAT - Machine Learning","volume":"50 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Functionally Constrained Algorithm Solves Convex Simple Bilevel Problems\",\"authors\":\"Huaqing Zhang, Lesi Chen, Jing Xu, Jingzhao Zhang\",\"doi\":\"arxiv-2409.06530\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper studies simple bilevel problems, where a convex upper-level\\nfunction is minimized over the optimal solutions of a convex lower-level\\nproblem. We first show the fundamental difficulty of simple bilevel problems,\\nthat the approximate optimal value of such problems is not obtainable by\\nfirst-order zero-respecting algorithms. Then we follow recent works to pursue\\nthe weak approximate solutions. For this goal, we propose novel near-optimal\\nmethods for smooth and nonsmooth problems by reformulating them into\\nfunctionally constrained problems.\",\"PeriodicalId\":501340,\"journal\":{\"name\":\"arXiv - STAT - Machine Learning\",\"volume\":\"50 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - STAT - Machine Learning\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.06530\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - STAT - Machine Learning","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.06530","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
This paper studies simple bilevel problems, where a convex upper-level
function is minimized over the optimal solutions of a convex lower-level
problem. We first show the fundamental difficulty of simple bilevel problems,
that the approximate optimal value of such problems is not obtainable by
first-order zero-respecting algorithms. Then we follow recent works to pursue
the weak approximate solutions. For this goal, we propose novel near-optimal
methods for smooth and nonsmooth problems by reformulating them into
functionally constrained problems.