Stefan M. Wild

Using Filter Methods to Guide Convergence for ADMM, with Applications to Nonnegative Matrix Factorization Problems

  • Robert Baraldi
  • Stefan M. Wild
  • Sven Leyffer
    • Categories Applications - Science and Engineering, Nonlinear Optimization Tags , , ,

    Nonconvex, nonlinear cost functions arise naturally in physical inverse problems and machine learning. The alternating direction method of multipliers (ADMM) has seen extensive use in these applications, despite exhibiting uncertain convergence behavior in many practical nonconvex settings, and struggling with general nonlinear constraints. In contrast, filter methods have proved effective in enforcing convergence for sequential … Read more

    Adaptive Sampling Quasi-Newton Methods for Zeroth-Order Stochastic Optimization

  • Raghu Bollapragada
  • Stefan M. Wild
    • Categories Convex Optimization, Nonlinear Optimization, Stochastic Programming Tags , ,

    We consider unconstrained stochastic optimization problems with no available gradient information. Such problems arise in settings from derivative-free simulation optimization to reinforcement learning. We propose an adaptive sampling quasi-Newton method where we estimate the gradients of a stochastic function using finite differences within a common random number framework. We develop modified versions of a norm … Read more

    Adaptive Sampling Quasi-Newton Methods for Derivative-Free Stochastic Optimization

  • Raghu Bollapragada
  • Stefan M. Wild
    • Categories Convex Optimization, Nonlinear Optimization, Stochastic Programming Tags , ,

    We consider stochastic zero-order optimization problems, which arise in settings from simulation optimization to reinforcement learning. We propose an adaptive sampling quasi-Newton method where we estimate the gradients of a stochastic function using finite differences within a common random number framework. We employ modified versions of a norm test and an inner product quasi-Newton test … Read more

    Derivative-free optimization methods

  • Jeffrey Larson
  • Matt Menickelly
  • Stefan M. Wild
    • Categories Nonlinear Optimization

    In many optimization problems arising from scientific, engineering and artificial intelligence applications, objective and constraint functions are available only as the output of a black-box or simulation oracle that does not provide derivative information. Such settings necessitate the use of methods for derivative-free, or zeroth-order, optimization. We provide a review and perspectives on developments in … Read more

    A Method for Convex Black-Box Integer Global Optimization

  • Jeffrey Larson
  • Sven Leyffer
  • Prashant Palkar
  • Stefan M. Wild
    • Categories Convex Optimization Tags , , ,

    We study the problem of minimizing a convex function on the integer lattice when the function cannot be evaluated at noninteger points. We propose a new underestimator that does not require access to (sub)gradients of the objective but, rather, uses secant linear functions that interpolate the objective function at previously evaluated points. These linear mappings … Read more

    Derivative-Free Robust Optimization by Outer Approximations

  • Matt Menickelly
  • Stefan M. Wild
    • Categories Nonsmooth Optimization, Robust Optimization, Unconstrained Optimization Tags , , ,

    We develop an algorithm for minimax problems that arise in robust optimization in the absence of objective function derivatives. The algorithm utilizes an extension of methods for inexact outer approximation in sampling a potentially infinite-cardinality uncertainty set. Clarke stationarity of the algorithm output is established alongside desirable features of the model-based trust-region subproblems encountered. We … Read more

    Manifold Sampling for Optimization of Nonconvex Functions that are Piecewise Linear Compositions of Smooth Components

  • Kamil Khan
  • Jeffrey Larson
  • Stefan M. Wild
    • Categories Nonsmooth Optimization, Unconstrained Optimization Tags , ,

    We develop a manifold sampling algorithm for the minimization of a nonsmooth composite function $f \defined \psi + h \circ F$ when $\psi$ is smooth with known derivatives, $h$ is a known, nonsmooth, piecewise linear function, and $F$ is smooth but expensive to evaluate. The trust-region algorithm classifies points in the domain of $h$ as … Read more

    Manifold Sampling for L1 Nonconvex Optimization

  • Jeffrey Larson
  • Matt Menickelly
  • Stefan M. Wild
    • Categories Nonlinear Optimization, Nonsmooth Optimization Tags , ,

    We present a new algorithm, called manifold sampling, for the unconstrained minimization of a nonsmooth composite function $h\circ F$ when $h$ has known structure. In particular, by classifying points in the domain of the nonsmooth function $h$ into manifolds, we adapt search directions within a trust-region framework based on knowledge of manifolds intersecting the current … Read more

    Randomized Derivative-Free Optimization of Noisy Convex Functions

  • Ruobing Chen
  • Stefan M. Wild
    • Categories Stochastic Programming, Unconstrained Optimization Tags , , ,

    We propose STARS, a randomized derivative-free algorithm for unconstrained optimization when the function evaluations are contaminated with random noise. STARS takes dynamic, noise-adjusted smoothing step-sizes that minimize the least-squares error between the true directional derivative of a noisy function and its finite difference approximation. We provide a convergence rate analysis of STARS for solving convex … Read more

    A Taxonomy of Constraints in Black-Box Simulation-Based Optimization

  • Sébastien Le Digabel
  • Stefan M. Wild
    • Categories Nonlinear Optimization, Optimization Software and Modeling Systems Tags , ,

    The types of constraints encountered in black-box simulation-based optimization problems differ significantly from those addressed in nonlinear programming. We introduce a characterization of constraints to address this situation. We provide formal definitions for several constraint classes and present illustrative examples in the context of the resulting taxonomy. This taxonomy, denoted KARQ, is useful for modeling … Read more