Ming Gu

CONVERGENCE RATE OF GRADIENT BASED ADAPTIVE RESTART FOR ACCELERATED GRADIENT SCHEMES

  • Shivkumar Chandrasekaran
  • Ming Gu
  • Can Kizilkale
    • Categories Convex and Nonsmooth Optimization Tags , , ,

    The accelerated gradient algorithm is known to have non-monotonic, periodic convergence behavior in the high momentum regime. If important function parameters like the condition number are known, the momentum can be adjusted to get linear convergence. Unfortunately these parameters are usually not accessible, so instead heuristics are used for deciding when to restart. One of … Read more

    PARNES: A rapidly convergent algorithm for accurate recovery of sparse and approximately sparse signals

  • Ming Gu
  • Lek-Heng Lim
  • Cinna Julie Wu
    • Categories Constrained Nonlinear Optimization, Convex Optimization, Optimization Software Benchmark Tags , , , , , , ,

    In this article we propose an algorithm, NESTA-LASSO, for the LASSO problem (i.e., an underdetermined linear least-squares problem with a one-norm constraint on the solution) that exhibits linear convergence under the restricted isometry property (RIP) and some other reasonable assumptions. Inspired by the state-of-the-art sparse recovery method, NESTA, we rely on an accelerated proximal gradient … Read more