A new polynomial-time algorithm for linear programming
Combinatorica
Mathematical Programming: Series A and B
Analog decoding using neural networks
AIP Conference Proceedings 151 on Neural Networks for Computing
Interior path following primal-dual algorithms. Part I: Linear programming
Mathematical Programming: Series A and B
A deterministic annealing approach to clustering
Pattern Recognition Letters
Parallel and Deterministic Algorithms from MRFs: Surface Reconstruction
IEEE Transactions on Pattern Analysis and Machine Intelligence
Neural Computation
Neural Computation
An analysis of the elastic net approach to the traveling salesman problem
Neural Computation
An Accurate and Efficient Bayesian Method for Automatic Segmentation of Brain MRI
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
A Double-Loop Algorithm to Minimize the Bethe Free Energy
EMMCVPR '01 Proceedings of the Third International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition
A novel optimizing network architecture with applications
Neural Computation
IEEE Transactions on Image Processing
A quadratic programming based cluster correspondence projection algorithm for fast point matching
Computer Vision and Image Understanding
A robust hybrid method for nonrigid image registration
Pattern Recognition
Shaping art with art: morphological analysis for investigating artistic reproductions
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part I
Hi-index | 0.00 |
In recent years there has been significant interest in adapting techniques from statistical physics, in particular mean field theory, to provide deterministic heuristic algorithms for obtaining approximate solutions to optimization problems. Although these algorithms have been shown experimentally to be successful there has been little theoretical analysis of them. In this paper we demonstrate connections between mean field theory methods and other approaches, in particular, barrier function and interior point methods. As an explicit example, we summarize our work on the linear assignment problem. In this previous work we defined a number of algorithms, including deterministic annealing, for solving the assignment problem. We proved convergence, gave bounds on the convergence times, and showed relations to other optimization algorithms.