No image
  • Mar 13, 1929
    (b.) -
    Jul 5, 1997


An American statistician, the re-discoverer of the Levenberg–Marquardt nonlinear least squares fitting algorithm. The LMA is a very popular curve-fitting algorithm used in many software applications for solving generic curve-fitting problems. In mathematics and computing, the Levenberg–Marquardt algorithm (LMA), also known as the damped least-squares (DLS) method, is used to solve non-linear least squares problems. These minimization problems arise especially in least squares curve fitting. The LMA interpolates between the Gauss–Newton algorithm (GNA) and the method of gradient descent. The LMA is more robust than the GNA, which means that in many cases it finds a solution even if it starts very far off the final minimum. For well-behaved functions and reasonable starting parameters, the LMA tends to be a bit slower than the GNA. LMA can also be viewed as Gauss–Newton using a trust region approach. He received his Bachelor’s degree in Physics and Mathematics from Columbia University in 1950 and his Master’s degree in Mathematics and statistics from the University of Delaware in 1956. He joined DuPont in 1953 and worked there for 39 years. He also founded and managed the DuPont Quality Management & Technology Center. In 1963 he published his famous paper "algorithm for least-squares estimation of nonlinear problems" in SIAM journal. He developed his algorithm to solve fitting nonlinear chemical models to laboratory data. As manager of the DuPont Applied Statistics Group, he led development of the Product Quality Management (PQM) methodology and computer systems that implemented the company's continuous improvement initiatives from the mid-1970s to the late 1990s. He served as President of the American Statistical Association and was an elected member of the International Statistical Institute. He was a founding member of the Registrar Accreditation Board (RAB) and served on the RAB Board of Directors since 1990. He was Chairman of the U.S. TAG to TC 176 and was a member of the Chairman's Strategic Advisory Group to ISO TC 176 and the Chairman's Advisory Group, U.S. TAG to TC 207 on Environmental Management. In 1991, he established his own company, Donald W. Marquardt and Associates, which provides consulting and training in quality management, quality assurance, ISO 9000 standards, applied statistics, strategic planning and organizational change. He was presented with numerous awards: President of the American Statistical Association (1986); Elected member of the International Statistical Institute; Leader of the U.S. delegation to the ISO 9000 International Quality Standard writing group; American Society for Quality (ASQ) Shewhart Medal (1987); American Statistical Association Statistician of the Year (1993–94); American Statistical Association Founders Award (1995); and American National Standards Institute Meritorious Service Award. He published more than 60 pieces of work, including research papers, book chapters and magazine articles.
  • Date of Birth:

    Mar 13, 1929
  • Date of Death:

    Jul 5, 1997
  • Noted For:

    Developer of an the LMA algorithm to solve fitting nonlinear chemical models to laboratory data, used in many software applications for solving generic curve-fitting problems
  • Category of Achievement:

  • More Info: