Inappropriate use of L-BFGS, Illustrated on frame field design

08/12/2015
by   Nicolas Ray, et al.
0

L-BFGS is a hill climbing method that is guarantied to converge only for convex problems. In computer graphics, it is often used as a black box solver for a more general class of non linear problems, including problems having many local minima. Some works obtain very nice results by solving such difficult problems with L-BFGS. Surprisingly, the method is able to escape local minima: our interpretation is that the approximation of the Hessian is smoother than the real Hessian, making it possible to evade the local minima. We analyse the behavior of L-BFGS on the design of 2D frame fields. It involves an energy function that is infinitly continuous, strongly non linear and having many local minima. Moreover, the local minima have a clear visual interpretation: they corresponds to differents frame field topologies. We observe that the performances of LBFGS are almost unpredictables: they are very competitive when the field is sampled on the primal graph, but really poor when they are sampled on the dual graph.

READ FULL TEXT
research
03/20/2020

A Graduated Filter Method for Large Scale Robust Estimation

Due to the highly non-convex nature of large-scale robust parameter esti...
research
08/29/2017

Natasha 2: Faster Non-Convex Optimization Than SGD

We design a stochastic algorithm to train any smooth neural network to ε...
research
07/13/2015

On Smooth 3D Frame Field Design

We analyze actual methods that generate smooth frame fields both in 2D a...
research
06/15/2020

Derivative-free global minimization for a class of multiple minima problems

We prove that the finite-difference based derivative-free descent (FD-DF...
research
01/28/2019

Depth creates no more spurious local minima

We show that for any convex differentiable loss function, a deep linear ...
research
11/13/2019

Existence of local minima of a minimal 2D pose-graph SLAM problem

In this paper, we show that for a minimal pose-graph problem, even in th...
research
01/04/2007

Statistical tools to assess the reliability of self-organizing maps

Results of neural network learning are always subject to some variabilit...

Please sign up or login with your details

Forgot password? Click here to reset