English
Related papers

Related papers: Gradient-based bilevel optimization for multi-pena…

200 papers

Penalized selection criteria like AIC or BIC are among the most popular methods for variable selection. Their theoretical properties have been studied intensively and are well understood, but making use of them in case of high-dimensional…

Methodology · Statistics 2016-04-27 Florian Frommlet , Gregory Nuel

In this study, we investigate learning rate adaption at different levels based on the hyper-gradient descent framework and propose a method that adaptively learns the optimizer parameters by combining multiple levels of learning rates with…

Machine Learning · Computer Science 2021-05-12 Renlong Jie , Junbin Gao , Andrey Vasnev , Minh-Ngoc Tran

Variational regularization techniques are dominant in the field of mathematical imaging. A drawback of these techniques is that they are dependent on a number of parameters which have to be set by the user. A by now common strategy to…

Optimization and Control · Mathematics 2020-12-10 Matthias J. Ehrhardt , Lindon Roberts

We consider simple bilevel optimization problems where the goal is to compute among the optimal solutions of a composite convex optimization problem, one that minimizes a secondary objective function. Our main contribution is threefold. (i)…

Optimization and Control · Mathematics 2025-04-14 Sepideh Samadi , Daniel Burbano , Farzad Yousefian

We investigate implicit regularization schemes for gradient descent methods applied to unpenalized least squares regression to solve the problem of reconstructing a sparse signal from an underdetermined system of linear measurements under…

Machine Learning · Statistics 2019-09-12 Tomas Vaškevičius , Varun Kanade , Patrick Rebeschini

Bilevel optimization aims to optimize an outer objective function that depends on the solution to an inner optimization problem. It is routinely used in Machine Learning, notably for hyperparameter tuning. The conventional method to compute…

Machine Learning · Computer Science 2024-02-27 Zhenzhang Ye , Gabriel Peyré , Daniel Cremers , Pierre Ablin

Recommendation models mainly deal with categorical variables, such as user/item ID and attributes. Besides the high-cardinality issue, the interactions among such categorical variables are usually long-tailed, with the head made up of…

Machine Learning · Computer Science 2019-05-29 Yihong Chen , Bei Chen , Xiangnan He , Chen Gao , Yong Li , Jian-Guang Lou , Yue Wang

We investigate the statistical behavior of gradient descent iterates with dropout in the linear regression model. In particular, non-asymptotic bounds for the convergence of expectations and covariance matrices of the iterates are derived.…

Statistics Theory · Mathematics 2025-03-19 Gabriel Clara , Sophie Langer , Johannes Schmidt-Hieber

Generalization is a central problem in Machine Learning. Indeed most prediction methods require careful calibration of hyperparameters usually carried out on a hold-out \textit{validation} dataset to achieve generalization. The main goal of…

Machine Learning · Statistics 2021-02-18 Karim Lounici , Katia Meziani , Benjamin Riu

We propose policy gradient algorithms for solving a risk-sensitive reinforcement learning (RL) problem in on-policy as well as off-policy settings. We consider episodic Markov decision processes, and model the risk using the broad class of…

Machine Learning · Computer Science 2024-06-25 Nithia Vijayan , Prashanth L. A

A number of popular transfer learning methods rely on grid search to select regularization hyperparameters that control over-fitting. This grid search requirement has several key disadvantages: the search is computationally expensive,…

Machine Learning · Computer Science 2025-01-28 Ethan Harvey , Mikhail Petrov , Michael C. Hughes

The extent to which the arbitrarily selected L2 regularization hyperparameter value affects the outcome of semantic segmentation with deep learning is demonstrated. Demonstrations rely on training U-net on small LGE-MRI datasets using the…

Image and Video Processing · Electrical Eng. & Systems 2021-09-03 Olivier Rukundo

Machine learning training methods depend plentifully and intricately on hyperparameters, motivating automated strategies for their optimisation. Many existing algorithms restart training for each new hyperparameter choice, at considerable…

Machine Learning · Computer Science 2022-04-22 Ross M. Clarke , Elre T. Oldewage , José Miguel Hernández-Lobato

Cross-validation is the workhorse of modern applied statistics and machine learning, as it provides a principled framework for selecting the model that maximizes generalization performance. In this paper, we show that the cross-validation…

Machine Learning · Statistics 2018-05-21 Shane Barratt , Rishi Sharma

Bilevel optimization has been developed for many machine learning tasks with large-scale and high-dimensional data. This paper considers a constrained bilevel optimization problem, where the lower-level optimization problem is convex with…

Machine Learning · Computer Science 2023-08-22 Siyuan Xu , Minghui Zhu

The tuning parameter selection strategy for penalized estimation is crucial to identify a model that is both interpretable and predictive. However, popular strategies (e.g., minimizing average squared prediction error via cross-validation)…

Methodology · Statistics 2022-11-10 Julia Holter , Jonathan Stallrich

We propose a multi-precision extension of the Quadratic Regularization (R2) algorithm that enables it to take advantage of low-precision computations, and by extension to decrease energy consumption during the solve. The lower the precision…

Optimization and Control · Mathematics 2023-12-14 Domnique Monnet , Dominique Orban

We study learning to learn for regression problems through the lens of hyperparameter tuning. We propose the Langevin Gradient Descent Algorithm (LGD), which approximates the mean of the posterior distribution defined by the loss function…

Machine Learning · Computer Science 2026-04-16 Saumya Goyal , Rohith Rongali , Ritabrata Ray , Barnabás Póczos

Learn to Optimize (L2O) trains deep neural network-based solvers for optimization, achieving success in accelerating convex problems and improving non-convex solutions. However, L2O lacks rigorous theoretical backing for its own training…

Machine Learning · Computer Science 2025-12-24 Qingyu Song , Wei Lin , Hong Xu

Gradient regularization (GR) is a method that penalizes the gradient norm of the training loss during training. While some studies have reported that GR can improve generalization performance, little attention has been paid to it from the…

Machine Learning · Computer Science 2023-02-06 Ryo Karakida , Tomoumi Takase , Tomohiro Hayase , Kazuki Osawa
‹ Prev 1 4 5 6 7 8 10 Next ›