English
Related papers

Related papers: Beyond Discretization: Learning the Optimal Soluti…

200 papers

Machine learning pipelines often rely on optimization procedures to make discrete decisions (e.g., sorting, picking closest neighbors, or shortest paths). Although these discrete decisions are easily computed, they break the…

Machine Learning · Computer Science 2020-06-11 Quentin Berthet , Mathieu Blondel , Olivier Teboul , Marco Cuturi , Jean-Philippe Vert , Francis Bach

Regularization is widely used in statistics and machine learning to prevent overfitting and gear solution towards prior information. In general, a regularized estimation problem minimizes the sum of a loss function and a penalty term. The…

Computation · Statistics 2012-01-18 Hua Zhou , Yichao Wu

For a variety of regularized optimization problems in machine learning, algorithms computing the entire solution path have been developed recently. Most of these methods are quadratic programs that are parameterized by a single parameter,…

Machine Learning · Computer Science 2012-10-31 Bernd Gärtner , Martin Jaggi , Clément Maria

Despite an extensive body of literature on deep learning optimization, our current understanding of what makes an optimization algorithm effective is fragmented. In particular, we do not understand well whether enhanced optimization…

Machine Learning · Computer Science 2024-03-04 Toki Tahmid Inan , Mingrui Liu , Amarda Shehu

Regularization is a widely recognized technique in mathematical optimization. It can be used to smooth out objective functions, refine the feasible solution set, or prevent overfitting in machine learning models. Due to its simplicity and…

Optimization and Control · Mathematics 2024-12-31 Filip Nikolovski , Irena Stojkovska , Katerina Hadzi-Velkova Saneva , Zoran Hadzi-Velkov

Many relevant problems in the area of systems and control, such as controller synthesis, observer design and model reduction, can be viewed as optimization problems involving dynamical systems: for instance, maximizing performance in the…

Optimization and Control · Mathematics 2023-11-15 Pascal Den Boef , Jos Maubach , Wil Schilders , Nathan van de Wouw

Popular machine learning estimators involve regularization parameters that can be challenging to tune, and standard strategies rely on grid search for this task. In this paper, we revisit the techniques of approximating the regularization…

Machine Learning · Statistics 2019-05-28 Eugene Ndiaye , Tam Le , Olivier Fercoq , Joseph Salmon , Ichiro Takeuchi

Multi-objective optimization (MOO) has become an influential framework in many machine learning problems with multiple objectives such as learning with multiple criteria and multi-task learning (MTL). In this paper, we propose a new…

Machine Learning · Computer Science 2023-11-30 Peiyao Xiao , Hao Ban , Kaiyi Ji

A framework is introduced for sequentially solving convex stochastic minimization problems, where the objective functions change slowly, in the sense that the distance between successive minimizers is bounded. The minimization problems are…

Optimization and Control · Mathematics 2018-03-12 Craig Wilson , Venugopal Veeravalli , Angelia Nedich

Path-following algorithms are frequently used in composite optimization problems where a series of subproblems, with varying regularization hyperparameters, are solved sequentially. By reusing the previous solutions as initialization,…

Optimization and Control · Mathematics 2021-12-10 Eugene Ndiaye , Ichiro Takeuchi

The selection of best variables is a challenging problem in supervised and unsupervised learning, especially in high dimensional contexts where the number of variables is usually much larger than the number of observations. In this paper,…

Methodology · Statistics 2024-04-01 Benoit Liquet , Sarat Moka , Samuel Muller

We study a class of fused lasso problems where the estimated parameters in a sequence are regressed toward their respective observed values (fidelity loss), with $\ell_1$ norm penalty (regularization loss) on the differences between…

Data Structures and Algorithms · Computer Science 2020-05-14 Cheng Lu

We consider distributed optimization under communication constraints for training deep learning models. We propose a new algorithm, whose parameter updates rely on two forces: a regular gradient step, and a corrective direction dictated by…

Machine Learning · Computer Science 2022-04-29 Yunfei Teng , Wenbo Gao , Francois Chalus , Anna Choromanska , Donald Goldfarb , Adrian Weller

We consider a suboptimal solution path algorithm for the Support Vector Machine. The solution path algorithm is an effective tool for solving a sequence of a parametrized optimization problems in machine learning. The path of the solutions…

Machine Learning · Computer Science 2011-05-04 Masayuki Karasuyama , Ichiro Takeuchi

We revisit the choice of SGD for training deep neural networks by reconsidering the appropriate geometry in which to optimize the weights. We argue for a geometry invariant to rescaling of weights that does not affect the output of the…

Machine Learning · Computer Science 2015-06-09 Behnam Neyshabur , Ruslan Salakhutdinov , Nathan Srebro

In this paper, we consider a general stochastic optimization problem which is often at the core of supervised learning, such as deep learning and linear classification. We consider a standard stochastic gradient descent (SGD) method with a…

Machine Learning · Statistics 2018-12-27 Lam M. Nguyen , Nam H. Nguyen , Dzung T. Phan , Jayant R. Kalagnanam , Katya Scheinberg

Two-stage methods addressing continuous shortest path problems start local minimization from discrete shortest paths in a spatial graph. The convergence of such hybrid methods to global minimizers hinges on the discretization error induced…

Optimization and Control · Mathematics 2022-04-13 Ralf Borndörfer , Fabian Danecker , Martin Weiser

Machine learning models trained with \emph{stochastic} gradient descent (SGD) can generalize better than those trained with deterministic gradient descent (GD). In this work, we study SGD's impact on generalization through the lens of the…

Machine Learning · Computer Science 2025-12-09 Hongjian Lan , Yucong Liu , Florian Schäfer

Stochastic gradient descent (SGD) is a simple and popular method to solve stochastic optimization problems which arise in machine learning. For strongly convex problems, its convergence rate was known to be O(\log(T)/T), by running SGD for…

Machine Learning · Computer Science 2015-03-19 Alexander Rakhlin , Ohad Shamir , Karthik Sridharan

We establish an equivalence between the $\ell_2$-regularized solution path for a convex loss function, and the solution of an ordinary differentiable equation (ODE). Importantly, this equivalence reveals that the solution path can be viewed…

Machine Learning · Statistics 2021-07-08 Yunzhang Zhu , Renxiong Liu
‹ Prev 1 2 3 10 Next ›