survey/proceedings on Statistical ML for Large-Scale Optimization

[Justin Boyan]

Colleagues,

At last year's IJCAI, Wray Buntine and I organized an IJCAI workshop
on the subject of applying statistical machine learning methods in
large-scale optimization domains.  With Arun Jagota's help, we have
now collected extended abstracts of all the presented work, and
several additional contributions, into a survey paper which we believe
contains the seeds of many exciting research directions.  Here's where
you can find it:

    http://www.icsi.berkeley.edu/~jagota/NCS/
    (click on "VOLUME 3")

I've attached the table of contents below.  We have also set up an
email list, learning-optimization at egroups.com, for discussion of
related topics.  If you'd like to join this list, please visit
egroups.com or use the sign-up form at

http://ic.arc.nasa.gov/people/jboyan/ijcai99/

Cheers,
Justin


      Statistical Machine Learning for Large-Scale Optimization

	Editors:  Justin Boyan, Wray Buntine, and Arun Jagota

  Contents:

  Introduction (J. Boyan)
  
  A Review of Iterative Global Optimization (K. Boese)
  
  Estimating the Number of Local Minima in Complex Search Spaces
  (R. Caruana and M. Mullins)
  
  Experimentally Determining Regions of Related Solutions for Graph
  Bisection Problems (T. Carson and R. Impagliazzo)
  
  Optimization of Parallel Search Using Machine Learning and Uncertainty 
  Reasoning (D. Cook, P. Gmytrasiewicz, and C. Tseng)
  
  Adaptive Heuristic Methods for Maximum Clique (A. Jagota and
  L. Sanchis)
  
  Probabilistic Modeling for Combinatorial Optimization (S. Baluja and
  S. Davies)
  
  Adaptive approaches to Clustering for Discrete Optimization
  (W. Buntine, L. Su and R. Newton)
  
  Building a Basic Block Instruction Scheduler with Reinforcement
  Learning and Rollouts (A. McGovern, E. Moss and A. Barto)
  
  STAGE Learning for Local Search (J. Boyan and A. Moore)
  
  Enhancing Discrete Optimization with Reinforcement Learning: Case
  Studies Using DARP (R. Moll, T. Perkins and A. Barto)
  
  Stochastic Optimization with Learning for Standard Cell Placement
  (L. Su, W. Buntine, R. Newton and B. Peters)
  
  Collective Intelligence for Optimization (D. Wolpert and K. Tumer)
  
  Efficient Value Function Approximation Using Regression Trees (X. Wang 
  and T. Dietterich)
  
  Numerical Methods for Very High-Dimension Vector Spaces (T. Dean,
  K. Kim, and S. Hazlehurst)


-- 
Justin A. Boyan        [Visiting Scientist from NASA Ames Research Center]
MIT Artificial Intelligence Lab                             jab at ai.mit.edu
545 Technology Square NE43-753        http://ic.arc.nasa.gov/people/jboyan
Cambridge, MA  02139              (617)-253-8005 voice, (617)-253-7781 fax