# Variational Optimization

Source: [Variational Optimization](<https://www.sota2.com/research/paper/68fa50041e209131ce967d22>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-04T05:01:55.649Z

Authors: Joe Staines, David Barber

Published: 2012-12-18T21:06:10.000Z

## Abstract

We discuss a general technique that can be used to form a differentiable bound on the optima of non-differentiable or discrete objective functions. We form a unified description of these methods and consider under which circumstances the bound is concave. In particular we consider two concrete applications of the method, namely sparse learning and support vector classification.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Lasso Regression on Synthetic Lasso Problem D=200](<https://www.sota2.com/research/sota/lasso-regression-on-synthetic-lasso-problem-d-200.md>): Lasso regression; Synthetic Lasso Problem D=200; Solution Time: 0.1308.

- [Lasso regression on Synthetic Lasso Problem D=50](<https://www.sota2.com/research/sota/lasso-regression-on-synthetic-lasso-problem-d-50.md>): Lasso regression; Synthetic Lasso Problem D=50; Solution Time: 0.1269.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1212.4507>)

[PDF](<https://arxiv.org/pdf/1212.4507.pdf>)