Optimizing the Modified Lam Annealing Schedule

Simulated annealing is a randomized algorithm which has been proposed for finding globally optimum least-cost configurations in large NP-complete problems with cost functions which may have many local minima. A theoretical analysis of simulated annealing based on its precise model, a time-inhomogeneous Markov chain, is presented. An annealing schedule is given for which the Markov chain is strongly ergodic and the algorithm converges to a global optimum. The finite-time behavior of simulated annealing is also analyzed and a bound obtained on the departure of the probability distribution of the state at finite time from the optimum. This bound gives an estimate of the rate of convergence and insights into the conditions on the annealing schedule which gives optimum performance.

Download Full-text

Criteria for an optimum simulated annealing schedule for problems of the travelling salesman type

Journal of Physics A General Physics ◽

10.1088/0305-4470/20/5/032 ◽

1987 ◽

Vol 20 (5) ◽

pp. 1239-1249 ◽

Cited By ~ 20

Author(s):

S Rees ◽

R C Ball

Keyword(s):

Simulated Annealing ◽

Annealing Schedule ◽

Travelling Salesman

Download Full-text

Adaptive simulated annealing schedule to the unit commitment problem

Electric Power Systems Research ◽

10.1016/j.epsr.2009.10.019 ◽

2010 ◽

Vol 80 (4) ◽

pp. 465-472 ◽

Cited By ~ 20

Author(s):

Grzegorz Dudek

Keyword(s):

Simulated Annealing ◽

Unit Commitment ◽

Annealing Schedule ◽

Unit Commitment Problem ◽

Commitment Problem ◽

Adaptive Simulated Annealing

Download Full-text

A Volatility Measure for Annealing in Feedback Neural Networks

Neural Computation ◽

10.1162/neco.1992.4.2.191 ◽

1992 ◽

Vol 4 (2) ◽

pp. 191-195 ◽

Cited By ~ 1

Author(s):

Joshua Alspector ◽

Torsten Zeppenfeld ◽

Stephan Luna

Keyword(s):

Neural Networks ◽

Specific Heat ◽

Reliable Method ◽

Mean Field ◽

Annealing Process ◽

Pattern Learning ◽

Annealing Schedule ◽

Speed Up ◽

Static Pattern ◽

Feedback Neural Networks

In feedback neural networks, especially for static pattern learning, a reliable method of settling is required. Simulated annealing has been used but it is often difficult to determine how to set the annealing schedule. Often the specific heat is used as a measure of when to slow down the annealing process, but this is difficult to measure. We propose another measure, volatility, which is easy to measure and related to the Edwards-Anderson model in spin-glass physics. This paper presents the concept of volatility, an argument for its similarity to specific heat, simulations of dynamics in Boltzmann and mean-field networks, and a method of using it to speed up learning.

Download Full-text