Regularized M|estimators with Nonconvexity

Bregman distance regularization for nonsmooth and nonconvex ...

Our approach leverages Bregman distances to generalize the classical quadratic regularization. By doing so, we generate a family of regularized ...

Dual Gradient Method for Time-Varying Nonconvex Optimization

A. Feedback-Based Regularized Primal-Dual Gradient Method for Time-Varying Nonconvex ... [7] M. Fazlyab, C. Nowzari, G. J. Pappas, A. Ribeiro, and V. M. ...

Gradient Descent with Proximal Average for Nonconvex and ...

We hope this algorithm can serve as a useful tool to further popularize the use of nonconvex regularization in challenging machine learning problems. ... Yuan, M.

Provable Nonconvex Methods/Algorithms - Ju Sun

Regularized M-estimators with nonconvexity: Statistical and algorithmic theory for local ptima (2013); High-dimensional regression with noisy and missing ...

A Cubic Regularization Approach for Finding Local Minimax Points ...

However, GDA has been proved to converge to stationary points for nonconvex minimax optimization, which are suboptimal compared with local minimax points. In ...

Optimality and complexity for constrained optimization problems with ...

The lp norm penalty function with 0

Regularization of limited memory quasi-Newton methods for large ...

... m inversion to two m\times m Cholesky factorizations. See [4] ... regularized Newton method for the unconstrained nonconvex optimization.

Matlab/Octave toolbox for nonconvex optimization - GitHub

Least square (linear regression); Linear SVM with quadratic Hinge loss; Linear logistic regression; Calibrated Hinge loss. The regularization terms g(x) that ...

Bregman iterative regularization using model functions for ... - Frontiers

, m , describing the model, and a vector b ∈ ℝm describing the possibly ... regularization, nonconvex nonsmooth minimization. Citation: Yang H, Zhang H ...

Combining Stochastic Adaptive Cubic Regularization with Negative ...

We focus on minimizing nonconvex finite-sum functions that typically arise in machine learning problems. In an attempt to solve this problem, the adaptive ...

Sharp Oracle Inequalities for Stationary Points of Nonconvex ...

Request PDF | Sharp Oracle Inequalities for Stationary Points of Nonconvex Penalized M-Estimators | Many statistical estimation procedures lead to nonconvex ...

inexact regularized Newton framework with a worst-case iteration ...

Abstract. An algorithm for solving smooth nonconvex optimization problems is proposed that, in the worst-case, takes ${\mathscr O}(\varepsilon ^{-3/2})$ it.

Implicit Regularization in Nonconvex Statistical Estimation - YouTube

Yuxin Chen, Princeton University https://simons.berkeley.edu/talks/yuxin-chen-11-29-17 Optimization, Statistics and Uncertainty.

Nonconvex Regularization for Network Slimming - UCI Mathematics

Alvarez, J.M., Salzmann, M.: Learning the number of neurons in deep networks. In: Advances in Neural Information Processing Systems. pp. 2270–2278 (2016). 3 ...

Nonconvex Penalized Regularization for Robust Sparse Recovery ...

Flamary, and M. Barlaud, “Nonconvex Regularization in. Remote Sensing,” IEEE Trans. Geosci. Remote Sens., vol. 54, no. 11, pp ...

Nonconvex optimization for statistical learning with structured sparsity

use nonconvex regularization terms. To solve our proposed model ... Loh and M. J. Wainwright, Regularized m-estimators with nonconvexity:.

Geometry and Regularization in Nonconvex Low-Rank Estimation

Theorem (PCA doesn't have spurious local minima, Baldi and Hornik, 1989). Suppose M has a strict eigen-gap between λr and λr+1, the.

On the Non-Asymptotic Properties of Regularized M-Estimators

We propose a general framework for regularization in M-estimation problems under time dependent (absolutely regular-mixing) data which encompasses many of the ...

Generalized Nonconvex Nonsmooth Low-Rank Minimization

of the matrix, solving the convex nuclear norm regularized problem leads to a near optimal low-rank solution [6]. ... ri + 1, ··· ,m}, where Pi ri = m, we can de-.

Nonlocal robust tensor recovery with nonconvex regularization

In this paper, we study robust tensor recovery for third-order tensors with different degradations, which aims to recover a tensor from partial observations ...