paper-with-me

홈 › Papers

Primal-Dual Rates and Certificates

2016-02-16 · Celestine Dünner, Simone Forte, Martin Takáč, Martin Jaggi

We propose an algorithm-independent framework to equip existing optimization methods with primal-dual certificates. Such certificates and corresponding rate of convergence guarantees are important for practitioners to diagnose progress, in particular in machine learning applications. We obtain new primal-dual convergence rates, e.g., for the Lasso as well as many L1, Elastic Net, group Lasso and TV-regularized problems. The theory applies to any norm-regularized generalized linear model. Our approach provides efficiently computable duality gaps which are globally defined, without modifying the original problems in the region of interest.

📄 PDF Abstract BibTeX arXiv:1602.05205

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine Learning

Similar Papers 제목 키워드 기반

Featurized Occupation Measures for Structured Global Search in Numerical Optimal Control

2026-03-17 · Qi Wei, Jianfeng Tao, Haoyang Tan, Hongyu Nie arxiv

Numerical optimal control has long been split between globally structured but dimensionally intractable Hamilton--Jacobi--Bellman (HJB) methods and scalable but local trajectory optimization. We introduce Featurized Occu…

Duality between subgradient and conditional gradient methods

2012-11-27 · Francis Bach

Given a convex optimization problem and its dual, there are many possible first-order algorithms. In this paper, we show the equivalence between mirror descent algorithms and algorithms generalizing the conditional gradi…

BIG-bench Machine Learning

Some Primal-Dual Theory for Subgradient Methods for Strongly Convex Optimization

2023-05-27 · Benjamin Grimmer, Danlin Li

We consider (stochastic) subgradient methods for strongly convex but potentially nonsmooth non-Lipschitz optimization. We provide new equivalent dual descriptions (in the style of dual averaging) for the classic subgradi…

Tight Robustness Certificates and Wasserstein Distributional Attacks for Deep Neural Networks

2025-10-11 · Bach C. Le, Tung V. Dao, Binh T. Nguyen, Hong T. M. Chu arxiv

Wasserstein distributionally robust optimization (WDRO) provides a framework for adversarial robustness, yet existing methods based on global Lipschitz continuity or strong duality often yield loose upper bounds or requi…

Adversarial Robustness

Restricted Dynamic Geometric Complexity: Certificates for Structured Preconditioning

2026-07-08 · Zavier Li arxiv

Optimization geometrodynamics views optimizer state as evolving geometry. Its full positive-definite quadratic benchmark gives the least affine-invariant deformation needed to reduce condition number when arbitrary metri…