variance reduction

Adaptive Importance Sampling Based Surrogation Methods for Bayesian Hierarchical Models, via Logarithmic Integral Optimization

  • Ziyu He
  • Junyi Liu
  • Jong-Shi Pang
    • Categories Constrained Nonlinear Optimization, Nonsmooth Optimization, Stochastic Programming Tags , ,

    We explore Maximum a Posteriori inference of Bayesian Hierarchical Models (BHMs) with intractable normalizers, which are increasingly prevalent in contemporary applications and pose computational challenges when combined with nonconvexity and nondifferentiability. To address these, we propose the Adaptive Importance Sampling-based Surrogation method, which efficiently handles nonconvexity and nondifferentiability while improving the sampling approximation of the … Read more

    Compromise Policy for Multi-stage Stochastic Linear Programming: Variance and Bias Reduction

  • Jiajun Xu
  • Suvrajeet Sen
    • Categories Applications - Science and Engineering, Dynamic Programming, Stochastic Programming Tags , , , , ,

    This paper focuses on algorithms for multi-stage stochastic linear programming (MSLP). We propose an ensemble method named the “compromise policy”, which not only reduces the variance of the function approximation but also reduces the bias of the estimated optimal value. It provides a tight lower bound estimate with a confidence interval. By exploiting parallel computing, … Read more

    Accelerating Stochastic Sequential Quadratic Programming for Equality Constrained Optimization using Predictive Variance Reduction

  • Albert S. Berahas
  • Jiahao Shi
  • Zihong Yi
  • Baoyu Zhou
    • Categories Constrained Nonlinear Optimization, Nonlinear Optimization Tags , , ,

    In this paper, we propose a stochastic variance reduction method for solving equality constrained optimization problems. Specifically, we develop a method based on the sequential quadratic programming paradigm that utilizes gradient approximations via predictive variance reduction techniques. Under reasonable assumptions, we prove that a measure of first-order stationarity evaluated at the iterates generated by our … Read more

    Training Structured Neural Networks Through Manifold Identification and Variance Reduction

  • Zih-Syuan Huang
  • Ching-pei Lee
    • Categories Nonlinear Optimization, Nonsmooth Optimization Tags , , , ,

    This paper proposes an algorithm, RMDA, for training neural networks (NNs) with a regularization term for promoting desired structures. RMDA does not incur computation additional to proximal SGD with momentum, and achieves variance reduction without requiring the objective function to be of the finite-sum form. Through the tool of manifold identification from nonlinear optimization, we … Read more

    Stochastic Variance-Reduced Prox-Linear Algorithms for Nonconvex Composite Optimization

  • Lin Xiao
  • Junyu Zhang
    • Categories Nonlinear Optimization, Stochastic Programming Tags , , ,

    We consider the problem of minimizing composite functions of the form $f(g(x))+h(x)$, where~$f$ and~$h$ are convex functions (which can be nonsmooth) and $g$ is a smooth vector mapping. In addition, we assume that $g$ is the average of finite number of component mappings or the expectation over a family of random component mappings. We propose … Read more

    Optimization for Supervised Machine Learning: Randomized Algorithms for Data and Parameters

  • Filip Hanzely
    • Categories Convex Optimization, Stochastic Programming Tags , , , , ,

    Many key problems in machine learning and data science are routinely modeled as optimization problems and solved via optimization algorithms. With the increase of the volume of data and the size and complexity of the statistical models used to formulate these often ill-conditioned optimization tasks, there is a need for new efficient algorithms able to … Read more

    Stochastic Variance-Reduced Prox-Linear Algorithms for Nonconvex Composite Optimization

  • Lin Xiao
  • Junyu Zhang
    • Categories Nonlinear Optimization, Nonsmooth Optimization, Stochastic Programming Tags , , , ,

    We consider minimization of composite functions of the form $f(g(x))+h(x)$, where $f$ and $h$ are convex functions (which can be nonsmooth) and $g$ is a smooth vector mapping. In addition, we assume that $g$ is the average of finite number of component mappings or the expectation over a family of random component mappings. We propose … Read more

    Variance Reduction of Stochastic Gradients Without Full Gradient Evaluation

  • Florian Jarre
  • Felix Lieder
    • Categories Unconstrained Optimization Tags ,

    A standard concept for reducing the variance of stochastic gradient approximations is based on full gradient evaluations every now and then. In this paper an approach is considered that — while approximating a local minimizer of a sum of functions — also generates approximations of the gradient and the function values without relying on full … Read more

    Inexact proximal stochastic second-order methods for nonconvex composite optimization

  • Xiao Wang
  • Hongchao Zhang
    • Categories Nonlinear Optimization Tags , , , , , ,

    In this paper, we propose a framework of Inexact Proximal Stochastic Second-order (IPSS) methods for solving nonconvex optimization problems, whose objective function consists of an average of finitely many, possibly weakly, smooth functions and a convex but possibly nons- mooth function. At each iteration, IPSS inexactly solves a proximal subproblem constructed by using some positive … Read more

    SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path Integrated Differential Estimator

  • Cong Fang
  • Chris Junchi Li
  • Zhouchen Lin
  • Tong Zhang
    • Categories Nonlinear Optimization, Stochastic Programming Tags , , , , ,

    In this paper, we propose a new technique named \textit{Stochastic Path-Integrated Differential EstimatoR} (SPIDER), which can be used to track many deterministic quantities of interest with significantly reduced computational cost. We apply SPIDER to two tasks, namely the stochastic first-order and zeroth-order methods. For stochastic first-order method, combining SPIDER with normalized gradient descent, we propose … Read more