Lintao Zhang, Sharad Malik

The Quest for Efficient Boolean Satisfiability Solvers
CAV 2002

Thomas Bartz–Beielstein and Sandor Markon.
Tuning Search Algorithms for Real-World
Applications: A Regression Tree Based Approach

In Congress on Evolutionary Computation (CEC'04)

Frank's slides

Donald R. Jones
A Taxonomy of Global Optimization Methods Based on Response Surfaces
Journal of Global Optimization 21: 345–383, 2001.

Brigham S. Anderson, Andrew W. Moore, and David Cohn.
A Nonparametric Approach to Noisy and Costly Optimization
In Proceedings of the 17th International Conference on Machine Learning, pp. 17-24

Mauro Brunato, Roberto Battiti and Srinivas Pasupuleti
A Memory-Based RASH Optimizer
AAAI 2006 Workshop

Merlise A. Clyde
Experimental Design: A Bayesian Perspective
Int. Encyc. Social and Behavioral Sciences 4 April 2001

Steven Coy, Bruce L. Golden, George C. Runger, Edward A. Wasil
Using Experimental Design to Find Effective Parameter Settings for Heuristics
Journal of Heuristics, 7: 77–97 (2000)

Philip Kilby, John Slaney, Sylvie Thiebaux, and Toby Walsh
Estimating Search Tree Size
AAAI 06 Workshop on Learning for Search

Shumeet Baluja and Scott Davies
Using Optimal Dependency-Trees for Combinatorial Optimization: Learning the Structure of the Search Space
In Proceedings of the Fourteenth Int. Conf. on Machine Learning (ICML 1997), pp. 30--38.

Meinolf Sellmann and Carlos Ansotegui
Disco – Novo – GoGo Integrating Local Search and Complete Search with Restarts
AAAI 06 Workshop on Learning for Search

Lin Xu, Frank Hutter, Holger Hoos, Kevin Leyton-Brown.

SATzilla-07: The Design and Analysis of an Algorithm Portfolio for SAT

Practice talk for CP

Eric I. Hsu and Matthew Kitching and Fahiem Bacchus and Sheila A. McIlraith

Using EM to Find Likely Assignments for Solving CSP's

Huan Liu and Lei Yu

Toward Integrating Feature Selection Algorithms for Classification and Clustering

Available online at http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1401889

Eric Sodomka, John Collins, and Maria Gini

Efficient Statistical Methods for Evaluating Trading Agent Performance

AAAI 07

Thomas G. Dietterich

Machine Learning for Sequential Data: A Review

Michail G. Lagoudakis and Michael L. Littman.

Learning to Select Branching Rules in the DPLL Procedure for Satisfiability

Slides by Ann Nowe based on the book by Sutton and Barto: http://www.cs.ualberta.ca/~sutton/book/ebook/the-book.html

Prasanna Balaprakash, Mauro Birattari, and Thomas Stuetzle

Improvement Strategies for the F-Race algorithm: Sampling Design and Iterative Refinement
Technical report

L. Mercier and P. Van Hentenryck.

Performance Analysis of Online Anticipatory Algorithms for Large Multistage Stochastic Integer Programs
One of two IJCAI 07 distinguished papers

A slide show is available at http://www.cs.brown.edu/people/mercier/slides/IJCAI_07_AnticipatoryAlg.html

Duc Nghia Pham, John Thornton, and Abdul Sattar

Building Structure into Local Search for SAT
One of two IJCAI 07 distinguished papers

Carla Gomes and Bart Selman. Artificial Intelligence Journal, Vol. 126, 2001, 43-62
Algorithm portfolios

Karl J. Lieberherr

Algorithmic extremal problems in combinatorial optimization
Journal of algorithms, 1982

Chris Bishop and Markus Svensen

Bayesian Hierarchical Mixtures of Experts
UAI 03

Interesting & relevant article in the economist, found by KLB:

Signs of the times
Why so much medical research is rot

http://www.economist.com/science/displaystory.cfm?story_id=8733754

Kamesh Madduri, David A. Bader, Jonathan W.Berry, and Joseph R. Crobak

An Experimental Study of a Parallel Shortest Path Algorithm for Solving Large-Scale Graph Instances
ALENEX 07

Matthew J. Streeter and Stephen F. Smith
A Simple Distribution-Free Approach to the Max k-Armed Bandit Problem
CP 06

Here is Matthew's presentation from CP

Frank talking about his ongoing research on local search for parameter tuning. Here are the slides

Cancelled because of Geoff Hinton's talk

Matteo Gagliolo and Juergen M. Schmidhuber.
Learning Restart Strategies
IJCAI 07

Arthur Brady and Lenore Cowen
Compact Routing on Power Law Graphs with Additive Stretch
In Proceedings of the 8th Workshop on Algorithm Engineering and Experiments and the Third Workshop on Analytic Algorithmics and Combinatorics, pages 119-128, 2006.

Continuation of Bayesian CART and start of Mick's presentation

Yuhong Wu, Hakon Tjelmeland and Mike West.
Bayesian CART - Prior Specification and Posterior Simulation.
Working paper. January 22, 2006

Continuation of:
Matteo Gagliolo and Juergen M. Schmidhuber
Impact of censored sampling on the performance of restart strategies.
To appear at CP 2006.

Matteo Gagliolo and Juergen M. Schmidhuber
Impact of censored sampling on the performance of restart strategies.
To appear at CP 2006.

I'll see Matteo at CP - if you have comments or questions please let me know.

Title: Novel Heuristic Search Methods for Protein Folding and Identification of Folding Pathways

Abstract: Proteins form the very basis of life. If we were to open up any living cell, we would find, apart from DNA and RNA molecules whose primary role is to store genetic information, a large number of different proteins that comprise the cell itself (for example the cell membrane and organelles), as well as a diverse set of enzymes that catalyze various metabolic reactions. If enzymes were absent, the cell would not be able to function, since a number of metabolic reactions would not be possible. Functions of proteins are the consequences of their functional 3D shape. Therefore, to control these versatile properties, we need to be able to predict the 3D shape of proteins; in other words, solve the protein folding problem. The prediction of a protein's conformation from its amino-acid sequence is currently one of the most prominent problems in molecular biology, biochemistry and bioinformatics. In this thesis, we address the protein folding problem and the closely-related problem of identifying folding pathways. The leading research objective for this work was to design efficient heuristic search algorithms for these problems, to empirically study these new methods and to compare them with existing algorithms.

This thesis makes the following contributions: (1) we show that biologically inspired approaches based on the notion of stigmergy – where a collection of agents modifies the environment, and those changes in turn affect the decision process of each agent (particularly artificial colonies of ants that give rise to such properties as self-organization and cooperation also observed in proteins) is a promising field of study for the protein folding problem; (2) we develop a novel adaptive search framework that is used to identify and to bin promising candidate solutions and to adaptively retrieve solutions when the search progress is unsatisfactory; (3) we develop a new method that efficiently explores large search neighbourhoods by performing biased iterated solution construction for identifying folding pathways; and (4) we show that our algorithms efficiently search the vast search landscapes encountered and are able to capture important aspects of the process of protein folding for some widely accepted computational models.

Belarmino Adenso-Díaz and Manuel Laguna,
Fine-tuning of Algorithms Using Fractional Experimental Design and Local Search Operations Research 54(1), 2006. (let me know if you want to access the paper and the above link doesn't work for you)

Here are my slides. There was a life demonstration of their CALIBRA software: I ran CALIBRA on the branin test function with a wrapper outputting which parameter settings are begin run into a file. Then I used Matlab to visualize that trajectory. I packed all this into a zip file.

My Summary:
The CALIBRA system combines fractional experimental design with a local search mechanism. Being limited to at most five free parameters, it starts off by evaluating each parameter configuration in a full factorial design. It then iteratively homes in to good regions in parameter space by employing fractional experimental designs that evaluate nine configurations around the so far best performing configuration. The grid for the experimental design becomes finer in each iteration, which provides a nice solution to the automatic discretization of continuous parameters. Once a local optimum is found and cannot be refined anymore, the search is restarted (with a coarser grid) by combining some of the best configurations found so far, but also introducing some noise for sake of diversification. The experiments reported in the paper show great promise in that CALIBRA was able to find parameter settings for six independent algorithms that matched or beat the respective originally proposed parameter configurations.

Model Counting: A New Strategy for Obtaining Good Bounds
Carla P. Gomes, Ashish Sabharwal, Bart Selman AAAI-06.
Proceedings of the 21st National Conference on Artificial Intelligence, pp 54-61, Boston, MA, Jul 2006. (Best paper award)

Here are the original slides of the AAAI talk

Efficient Global Optimization of Expensive Black Box Functions

Donald R. Jones, Matthias Schonlau, William J. Welch. Journal of Global Optimization (?), 1998.

This is very well written and the basis of section 6.3.5 of the DACE book.

Fractional Factorial Experiments, chapters 7-8 in the book
Clint's slides

Analysis-of-variance, chapters 6 in the book
Jacek's slides and anova in Matlab

Design of Factorial Experiments, chapters 4-5 in the book, finished by Kevin LB: Here's Kevin's slides

Analysis-of-variance, chapters 6 in the book; started by Jacek

Design of Factorial Experiments, chapters 4-5 in the book, to be finished
Here's Kevin's slides

Talk by and meeting with David Johnson.

Nov 18, 2004

“Designing and Reporting Computational Experiments with Heuristic Methods” by Barr, R. S., B. L. Golden, J. P. Kelly, M. G. C. Resende and W. R. Stewart (1995). [pdf] continued

and some stuff on Statistical Design of Experiments Dan will let us know about soon ...

Nov 4, 2004

“Designing and Reporting Computational Experiments with Heuristic Methods” by Barr, R. S., B. L. Golden, J. P. Kelly, M. G. C. Resende and W. R. Stewart (1995). [pdf]

Multi-Agent Algorithms for Solving Graphical Games [pdf] (continued)

and Multi-agent oriented constraint satisfaction [pdf] (local search for CSP cast as collaborating agents)

Multi-Agent Algorithms for Solving Graphical Games [pdf]

This is a local search paper for a compact set of games called graphical games (basically Bayes nets for games)

Simple Search Methods for Finding a Nash Equilibrium [pdf]

This paper concerns complete search.

Relevant Sections (4.5 pages):
3.2 Application of ACO Algorithm to Dynamic Combinatorial Optimisation Problem (an example of application ACO to Network Routing)
3.2.1 Connection-Oriented Network Routing
3.2.2 Connectionless Network Routing