We consider variants of trust-region and adaptive cubic regularization methods for non-
convex optimization, in which the Hessian matrix is approximated. Under certain condition …

For large-scale finite-sum minimization problems, we study non-asymptotic and high-
probability global as well as local convergence properties of variants of Newton's method …

Optimization plays an important role in solving many inverse problems. Indeed, the task of
inversion often either involves or is fully cast as a solution of an optimization problem. In this …

Abstract The emergence of Big Data has enabled new research perspectives in the discrete
choice community. While the techniques to estimate Machine Learning models on a massive …

We propose a fast Newton hard thresholding pursuit algorithm for sparsity constrained
nonconvex optimization. Our proposed algorithm reduces the per-iteration time complexity to …

Differentiable bilevel Neural Architecture Search (NAS) has emerged as a powerful
approach in automated machine learning (AutoML) for efficiently searching for neural …

In this work, we present probabilistic local convergence results for a stochastic semismooth
Newton method for a class of stochastic composite optimization problems involving the sum …

In supervised learning using kernel methods, we often encounter a large-scale finite-sum
minimization over a reproducing kernel Hilbert space (RKHS). Large-scale finite-sum …

Abstract The emergence of Big Data opened research to new perspectives for the discrete
choice community. While the Machine Learning (ML) community has been thriving in finding …

Due to the large-scale nature of many modern machine learning applications, including but
not limited to deep learning problems, people have been focusing on studying and …