Towards a deeper geometric, analytic and algorithmic understanding of margins
From MaRDI portal
Publication:2815511
DOI10.1080/10556788.2015.1099652zbMath1382.90056arXiv1406.5311OpenAlexW3105498960MaRDI QIDQ2815511
Aaditya Ramdas, Javier F. Peña
Publication date: 29 June 2016
Published in: Optimization Methods and Software (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1406.5311
Related Items (6)
Sampling Kaczmarz-Motzkin method for linear feasibility problems: generalization and acceleration ⋮ Accelerated sampling Kaczmarz Motzkin algorithm for the linear feasibility problem ⋮ New characterizations of Hoffman constants for systems of linear constraints ⋮ The condition number of a function relative to a set ⋮ Bias of homotopic gradient descent for the hinge loss ⋮ Randomized Gradient Boosting Machine
Cites Work
- First-order algorithm with \({\mathcal{O}(\ln(1/\epsilon))}\) convergence for \({\epsilon}\)-equilibrium in two-person zero-sum games
- Convex analysis and nonlinear optimization. Theory and examples.
- Some perturbation theory for linear programming
- Some characterizations and properties of the ``distance to the ill-posedness and the condition measure of a conic linear system
- A Primal–Dual Smooth Perceptron–von Neumann Algorithm
- The Perceptron: A Model for Brain Functioning. I
- The Relaxation Method for Solving Systems of Linear Inequalities
- Approximations to Solutions to Systems of Linear Inequalities
- Incorporating Condition Measures into the Complexity Theory of Linear Programming
- An Iterative Procedure for Computing the Minimum of a Quadratic Form on a Convex Set
- A new condition number for linear programming
This page was built for publication: Towards a deeper geometric, analytic and algorithmic understanding of margins
