Cyril Fonlupt

Parallel ant colonies for the quadratic assignment problem

Ant Colonies optimization take inspiration from the behavior of real ant colonies to solve optimization problems. This paper presents a parallel model for ant colonies to solve the quadratic assignment problem (QAP). The cooperation between simulated ants is provided by a pheromone matrix that plays the role of a global memory. The exploration of the search space is guided by the evolution of pheromones levels, while exploitation has been boosted by a tabu local search heuristic. Special care has also been taken in the design of a diversification phase, based on a frequency matrix. We give results that have been obtained on benchmarks from the QAP library. We show that they compare favorably with other algorithms dedicated for the QAP.

Parallel Ant Colonies for Combinatorial Optimization Problems

Ant Colonies (AC) optimization take inspiration from the behavior of real ant colonies to solve optimization problems. This paper presents a parallel model for ant colonies to solve the quadratic assignment problem (QAP). Parallelism demonstrates that cooperation between communicating agents improve the obtained results in solving the QAP. It demonstrates also that high-performance computing is feasible to solve large optimization problems.

Population parallel GP on the G80 GPU

The availability of low cost powerful parallel graphics cards has stimulated a trend to port GP on Graphics Processing Units (GPUs). Previous works on GPUs have shown evaluation phase speedups for large training cases sets. Using the CUDA language on the G80 GPU, we show it is possible to efficiently interpret several GP programs in parallel, thus obtaining speedups also for small training sets starting at less than 100 training cases. Our scheme was embedded in the well-known ECJ library, providing an easy entry point for owners of G80 GPUs.

Genetic programming on graphics processing units

The availability of low cost powerful parallel graphics cards has stimulated the port of Genetic Programming (GP) on Graphics Processing Units (GPUs). Our work focuses on the possibilities offered by Nvidia G80 GPUs when programmed in the CUDA language. In a first work we have showed that this setup allows to develop fine grain parallelization schemes to evaluate several GP programs in parallel, while obtaining speedups for usual training sets and program sizes. Here we present another parallelization scheme and optimizations about program representation and use of GPU fast memory. This increases the computation speed about three times faster, up to 4 billion GP operations per second. The code has been developed within the well known ECJ library and is open source.

High performance genetic programming on GPU

The availability of low cost powerful parallel graphics cards has stimulated the port of Genetic Programming (GP) on Graphics Processing Units (GPUs). Our work focuses on the possibilities offered by Nvidia G80 GPUs when programmed in the CUDA language. We compare two parallelization schemes that evaluate several GP programs in parallel. We show that the fine grain distribution of computations over the elementary processors greatly impacts performances. We also present memory and representation optimizations that further enhance computation speed, up to 2.8 billion GP operations per second. The code has been developed with the well known ECJ library.

Data-parallel load balancing stategies

Abstract Programming irregular and dynamic data-parallel algorithms must consider the effect of data distribution. The implementation of a load balancing algorithm is quite a difficult task for the programmer. However, a load balancing strategy may be developed independently of the application. The integration of such a strategy into the data-parallel algorithm may be relevant to a library or a data-parallel compiler run-time. We propose load distribution data-parallel algorithms for a class of irregular data-parallel algorithms called stack algorithms. Our algorithms allow the use of regular and/or irregular communication patterns to exchange the works between processors. The results of theoretical analysis of these algorithms are presented. They allow different load balancing algorithms to be compared and the identification of criteria to choose between them.

Solving the ocean color problem using a genetic programming approach

Abstract The ocean color problem consists in evaluating ocean components concentrations (phytoplankton, sediment and yellow substance) from sunlight reflectance or luminance values at selected wavelengths in the visible band. The interest of this application increases with the availability of new satellite sensors. Moreover, monitoring phytoplankton concentrations is a key point for a wide set of problems ranging from greenhouse effect to industrial fishing and signaling toxic algae blooms. To our knowledge, it is the first attempt at this regression problem with genetic programming (GP). We show that GP outperforms traditional polynomial fits and rivals artificial neural nets in the case of open ocean waters. We improve previous works by also solving a range of coastal waters types, providing detailed results on estimation errors. To our knowledge, we are the firsts to publish numerical results regarding coastal waters. Experiments were conducted with a dynamic fitness GP algorithm in order to speed up computing time through a process of progressive learning.

Tarpeian bloat control and generalization accuracy

In this paper we focus on machine-learning issues solved with Genetic Programming (GP). Excessive code growth or bloat often happens in GP, greatly slowing down the evolution process. In Pol03, Poli proposed the Tarpeian Control method to reduce bloat, but possible side-effects of this method on the generalization accuracy of GP hypotheses remained to be tested. In particular, since Tarpeian Control puts a brake on code growth, it could behave as a kind of Occams razor, promoting shorter hypotheses more able to extend their knowledge to cases apart from any learning steps. To answer this question, we experiment Tarpeian Control with symbolic regression. The results are contrasted, showing that it can either increase or reduce the generalization power of GP hypotheses, depending on the problem at hand. Experiments also confirm the decrease in size of programs. We conclude that Tarpeian Control might be useful if carefully tuned to the problem at hand.

Exploring Overfitting in Genetic Programming

The problem of overfitting (focusing closely on examples at the loss of generalization power) is encountered in all supervised machine learning schemes. This study is dedicated to explore some aspects of overfitting in the particular case of genetic programming. After recalling the causes usually invoked to explain overfitting such as hypothesis complexity or noisy learning examples, we test and compare the resistance to overfitting on three variants of genetic programming algorithms (basic GP, sizefair crossover GP and GP with boosting) on two benchmarks, a symbolic regression and a classification problem. We propose guidelines based on these results to help reduce overfitting with genetic programming.

A Bit-Wise Epistasis Measure for Binary Search Spaces

The epistatic variance has been introduced by Davidor as a tool for the evaluation of interdependences between genes, thus possibly giving clues about the difficulty of optimizing functions with genetic algorithms (GAs). Despite its theoretical grounding in Walsh function analysis, several studies have shown its weakness as a predictor of GAs results. In this paper, we focus on binary search spaces and propose to measure epistatic effect on the level of individual genes, an approach that we call bit-wise epistasis. We give examples of this measure on several well-known test problems, then we take into account this supplementary information to improve the performances of evolutionary algorithms. We conclude by pointing towards possible extensions of this concept to real size problems.