Salar Fattahi

Implicit Regularization of Sub-Gradient Method in Robust Matrix Recovery: Don’t be Afraid of Outliers

  • Salar Fattahi
  • Jianhao Ma
    • Categories Nonlinear Optimization, Nonsmooth Optimization, Statistics Tags , ,

    It is well-known that simple short-sighted algorithms, such as gradient descent, generalize well in the over-parameterized learning tasks, due to their implicit regularization. However, it is unknown whether the implicit regularization of these algorithms can be extended to robust learning tasks, where a subset of samples may be grossly corrupted with noise. In this work, … Read more

    Scalable Inference of Sparsely-changing Markov Random Fields with Strong Statistical Guarantees

  • Salar Fattahi
  • Andrés Gómez
    • Categories Combinatorial Optimization, Statistics Tags , ,

    In this paper, we study the problem of inferring time-varying Markov random fields (MRF), where the underlying graphical model is both sparse and changes sparsely over time. Most of the existing methods for the inference of time-varying MRFs rely on the regularized maximum likelihood estimation (MLE), that typically suffer from weak statistical guarantees and high … Read more