stochastic gradient

Alternate Training of Shared and Task-Specific Parameters for Multi-Task Neural Networks

  • Stefania Bellavia
    • Categories Nonlinear Optimization, Stochastic Programming Tags , ,

    This paper introduces novel alternate training procedures for hard-parameter sharing Multi-Task Neural Networks (MTNNs). Traditional MTNN training faces challenges in managing conflicting loss gradients, often yielding sub-optimal performance. The proposed alternate training method updates shared and task-specific weights alternately, exploiting the multi-head architecture of the model. This approach reduces computational costs, enhances training regularization, and … Read more

    A Stochastic-Gradient-based Interior-Point Algorithm for Solving Smooth Bound-Constrained Optimization Problems

  • Qi Wang
  • Frank E. Curtis
  • Daniel P. Robinson
  • Vyacheslav Kungurtsev
    • Categories Constrained Nonlinear Optimization, Nonlinear Optimization, Optimization in Data Science Tags , ,

    A stochastic-gradient-based interior-point algorithm for minimizing a continuously differentiable objective function (that may be nonconvex) subject to bound constraints is presented, analyzed, and demonstrated through experimental results. The algorithm is unique from other interior-point methods for solving smooth (nonconvex) optimization problems since the search directions are computed using stochastic gradient estimates. It is also unique … Read more

    A momentum-based linearized augmented Lagrangian method for nonconvex constrained stochastic optimization

  • Qiankun Shi
  • Xiao Wang
  • Hao Wang
    • Categories Constrained Nonlinear Optimization, Nonlinear Optimization, Stochastic Programming Tags , , , , ,

    Nonconvex constrained stochastic optimization has emerged in many important application areas. Subject to general functional constraints it minimizes the sum of an expectation function and a nonsmooth regularizer. Main challenges arise due to the stochasticity in the random integrand and the possibly nonconvex functional constraints. To address these issues we propose a momentum-based linearized augmented … Read more

    New Penalized Stochastic Gradient Methods for Linearly Constrained Strongly Convex Optimization

  • Meng Li
  • Paul Grigas
  • Alper Atamturk
    • Categories Constrained Nonlinear Optimization, Convex Optimization Tags , , , ,

    For minimizing a strongly convex objective function subject to linear inequality constraints, we consider a penalty approach that allows one to utilize stochastic methods for problems with a large number of constraints and/or objective function terms. We provide upper bounds on the distance between the solutions to the original constrained problem and the penalty reformulations, … 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

    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

    A linearly convergent stochastic recursive gradient method for convex optimization

  • Tiande Guo
  • Yan Liu
  • Xiao Wang
    • Categories Convex and Nonsmooth Optimization, Convex Optimization Tags , , , ,

    The stochastic recursive gradient algorithm (SARAH) [8] attracts much interest recently. It admits a simple recursive framework for updating stochastic gradient estimates. Motivated by this, in this paper, we propose a SARAH-I method incorporating importance sampling, whose linear conver- gence rate of the sequence of distances between iterates and the optima set is proven under … Read more

    Generalized Stochastic Frank-Wolfe Algorithm with Stochastic “Substitute” Gradient for Structured Convex Optimization

  • Robert M. Freund
  • Haihao Lu
    • Categories Convex Optimization, Nonlinear Optimization, Stochastic Programming Tags , , ,

    The stochastic Frank-Wolfe method has recently attracted much general interest in the context of optimization for statistical and machine learning due to its ability to work with a more general feasible region. However, there has been a complexity gap in the guaranteed convergence rate for stochastic Frank-Wolfe compared to its deterministic counterpart. In this work, … Read more

    The Adaptive Sampling Gradient Method: Optimizing Smooth Functions with an Inexact Oracle

  • Fatemeh Hashemi
  • Raghu Pasupathy
  • Michael Taaffe
    • Categories Nonlinear Optimization, Optimization of Simulated Systems, Stochastic Programming Tags , ,

    Consider settings such as stochastic optimization where a smooth objective function $f$ is unknown but can be estimated with an \emph{inexact oracle} such as quasi-Monte Carlo (QMC) or numerical quadrature. The inexact oracle is assumed to yield function estimates having error that decays with increasing oracle effort. For solving such problems, we present the Adaptive … Read more

    Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Lojasiewicz Condition

  • Hamed Karimi
  • Mark Schmidt
  • Julie Nutini
    • Categories Convex and Nonsmooth Optimization Tags , , , , , , , ,

    In 1963, Polyak proposed a simple condition that is sufficient to show a global linear convergence rate for gradient descent. This condition is a special case of the Lojasiewicz inequality proposed in the same year, and it does not require strong convexity (or even convexity). In this work, we show that this much-older Polyak-Lojasiewicz (PL) … Read more