English
Related papers

Related papers: Linearly-constrained nonsmooth optimization for tr…

200 papers

We introduce a general framework for analyzing learning algorithms based on the notion of self-regularization, which captures implicit complexity control without requiring explicit regularization. This is motivated by previous observations…

Machine Learning · Statistics 2026-03-19 Max Schölpple , Liu Fanghui , Ingo Steinwart

Regularization is a critical component in deep learning. The most commonly used approach, weight decay, applies a constant penalty coefficient uniformly across all parameters. This may be overly restrictive for some parameters, while…

Machine Learning · Computer Science 2024-12-10 Jörg K. H. Franke , Michael Hefenbrock , Gregor Koehler , Frank Hutter

We present a new algorithm for solving optimization problems with objective functions that are the sum of a smooth function and a (potentially) nonsmooth regularization function, and nonlinear equality constraints. The algorithm may be…

Optimization and Control · Mathematics 2024-04-12 Yutong Dai , Xiaoyi Qu , Daniel P. Robinson

To accelerate DNNs inference, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations. Several previous works attempted to directly approximate a pre-trained model by low-rank…

Computer Vision and Pattern Recognition · Computer Science 2020-01-27 Yuhui Xu , Yuxi Li , Shuai Zhang , Wei Wen , Botao Wang , Wenrui Dai , Yingyong Qi , Yiran Chen , Weiyao Lin , Hongkai Xiong

Optimization with nonnegative orthogonality constraints has wide applications in machine learning and data sciences. It is NP-hard due to some combinatorial properties of the constraints. We first propose an equivalent optimization…

Optimization and Control · Mathematics 2021-01-01 Bo Jiang , Xiang Meng , Zaiwen Wen , Xiaojun Chen

Variable selection is an old and pervasive problem in regression analysis. One solution is to impose a lasso penalty to shrink parameter estimates toward zero and perform continuous model selection. The lasso-penalized mixture of linear…

Applications · Statistics 2016-05-04 Luke R. Lloyd-Jones , Hien D. Nguyen , Geoffrey J. McLachlan

In analyzing and assessing the condition of dynamical systems, it is necessary to account for nonlinearity. Recent advances in computation have rendered previously computationally infeasible analyses readily executable on common computer…

Computational Engineering, Finance, and Science · Computer Science 2021-09-24 Thomas Simpson , Nikolaos Dervilis , Eleni Chatzi

We provide theoretical analysis of the statistical and computational properties of penalized $M$-estimators that can be formulated as the solution to a possibly nonconvex optimization problem. Many important estimators fall in this…

Machine Learning · Statistics 2015-01-28 Zhaoran Wang , Han Liu , Tong Zhang

Nonconvex regularization has been popularly used in low-rank matrix learning. However, extending it for low-rank tensor learning is still computationally expensive. To address this problem, we develop an efficient solver for use with a…

Machine Learning · Computer Science 2022-05-09 Quanming Yao , Yaqing Wang , Bo Han , James Kwok

While much work has been devoted to understanding the implicit (and explicit) regularization of deep nonlinear networks in the supervised setting, this paper focuses on unsupervised learning, i.e., autoencoders are trained with the…

Machine Learning · Computer Science 2021-10-25 Harald Steck , Dario Garcia Garcia

We provide novel theoretical results regarding local optima of regularized $M$-estimators, allowing for nonconvexity in both loss and penalty functions. Under restricted strong convexity on the loss and suitable regularity conditions on the…

Statistics Theory · Mathematics 2015-01-05 Po-Ling Loh , Martin J. Wainwright

Low-rank learning has attracted much attention recently due to its efficacy in a rich variety of real-world tasks, e.g., subspace segmentation and image categorization. Most low-rank methods are incapable of capturing low-dimensional…

Computer Vision and Pattern Recognition · Computer Science 2016-11-16 Ping Li , Jun Yu , Meng Wang , Luming Zhang , Deng Cai , Xuelong Li

The goal of this paper is to find a low-rank approximation for a given tensor. Specifically, we give a computable strategy on calculating the rank of a given tensor, based on approximating the solution to an NP-hard problem. In this paper,…

Numerical Analysis · Mathematics 2016-10-20 Xiaofei Wang , Carmeliza Navasca

Low-rank representation (LRR) is an effective method for subspace clustering and has found wide applications in computer vision and machine learning. The existing LRR solver is based on the alternating direction method (ADM). It suffers…

Optimization and Control · Mathematics 2011-09-05 Zhouchen Lin , Risheng Liu , Zhixun Su

We consider a class of constrained optimization problems with a possibly nonconvex non-Lipschitz objective and a convex feasible set being the intersection of a polyhedron and a possibly degenerate ellipsoid. Such problems have a wide range…

Optimization and Control · Mathematics 2016-04-08 Xiaojun Chen , Zhaosong Lu , Ting Kei Pong

We develop a family of accelerated stochastic algorithms that minimize sums of convex functions. Our algorithms improve upon the fastest running time for empirical risk minimization (ERM), and in particular linear least-squares regression,…

Machine Learning · Statistics 2015-06-25 Roy Frostig , Rong Ge , Sham M. Kakade , Aaron Sidford

In this work, we propose a new training method for finding minimum weight norm solutions in over-parameterized neural networks (NNs). This method seeks to improve training speed and generalization performance by framing NN training as a…

Machine Learning · Statistics 2018-06-22 Yamini Bansal , Madhu Advani , David D Cox , Andrew M Saxe

We develop fast algorithms and robust software for convex optimization of two-layer neural networks with ReLU activation functions. Our work leverages a convex reformulation of the standard weight-decay penalized training problem as a set…

Machine Learning · Computer Science 2025-04-10 Aaron Mishkin , Arda Sahiner , Mert Pilanci

We present and analyze a novel regularized form of the gradient clipping algorithm, proving that it converges to global minima of the loss surface of deep neural networks under the squared loss, provided that the layers are of sufficient…

Machine Learning · Computer Science 2025-04-09 Matteo Tucat , Anirbit Mukherjee , Procheta Sen , Mingfei Sun , Omar Rivasplata

Distributed training of $l_1$ regularized classifiers has received great attention recently. Most existing methods approach this problem by taking steps obtained from approximating the objective by a quadratic approximation that is…

Machine Learning · Computer Science 2016-11-25 Dhruv Mahajan , S. Sathiya Keerthi , S. Sundararajan