English
Related papers

Related papers: Understanding the Generalization of Bilevel Progra…

200 papers

Methods for solving scientific computing and inference problems, such as kernel- and neural network-based approaches for partial differential equations (PDEs), inverse problems, and supervised learning tasks, depend crucially on the choice…

Machine Learning · Statistics 2025-10-08 Nicholas H. Nelsen , Houman Owhadi , Andrew M. Stuart , Xianjin Yang , Zongren Zou

Bilevel optimization has found successful applications in various machine learning problems, including hyper-parameter optimization, data cleaning, and meta-learning. However, its huge computational cost presents a significant challenge for…

Machine Learning · Computer Science 2024-11-05 Xiaoyu Wang , Rui Pan , Renjie Pi , Jipeng Zhang

Large reasoning models (LRMs) generate intermediate reasoning traces before producing final answers, yielding strong gains on multi-step and mathematical tasks. Yet aligning LRMs with human preferences, a crucial prerequisite for model…

Machine Learning · Computer Science 2025-10-07 Mingkang Zhu , Xi Chen , Bei Yu , Hengshuang Zhao , Jiaya Jia

Modern machine learning methods are often overparametrized, allowing adaptation to the data at a fine level. This can seem puzzling; in the worst case, such models do not need to generalize. This puzzle inspired a great amount of work,…

Machine Learning · Statistics 2021-06-10 Licong Lin , Edgar Dobriban

Bayesian optimization (BO) is a widely popular approach for the hyperparameter optimization (HPO) in machine learning. At its core, BO iteratively evaluates promising configurations until a user-defined budget, such as wall-clock time or…

This paper is about how to partition decision variables while decomposing a large-scale optimization problem for the best performance of distributed solution methods. Solving a large-scale optimization problem sequen- tially can be…

Optimization and Control · Mathematics 2017-10-26 Yuchen Zheng , Ilbin Lee , Nicoleta Serban

Deep neural networks have seen great success in recent years; however, training a deep model is often challenging as its performance heavily depends on the hyper-parameters used. In addition, finding the optimal hyper-parameter…

Automated hyperparameter optimization (HPO) has gained great popularity and is an important ingredient of most automated machine learning frameworks. The process of designing HPO algorithms, however, is still an unsystematic and manual…

Recent work on hyperparameters optimization (HPO) has shown the possibility of training certain hyperparameters together with regular parameters. However, these online HPO algorithms still require running evaluation on a set of validation…

Machine Learning · Computer Science 2021-01-19 Jingkang Wang , Mengye Ren , Ilija Bogunovic , Yuwen Xiong , Raquel Urtasun

Tuning hyperparameters of learning algorithms is hard because gradients are usually unavailable. We compute exact gradients of cross-validation performance with respect to all hyperparameters by chaining derivatives backwards through the…

Machine Learning · Statistics 2015-04-03 Dougal Maclaurin , David Duvenaud , Ryan P. Adams

With the extensive applications of machine learning models, automatic hyperparameter optimization (HPO) has become increasingly important. Motivated by the tuning behaviors of human experts, it is intuitive to leverage auxiliary knowledge…

Machine Learning · Computer Science 2022-06-07 Yang Li , Yu Shen , Huaijun Jiang , Wentao Zhang , Zhi Yang , Ce Zhang , Bin Cui

Modern machine learning models are often constructed taking into account multiple objectives, e.g., minimizing inference time while also maximizing accuracy. Multi-objective hyperparameter optimization (MHPO) algorithms return such…

Machine Learning · Computer Science 2024-02-29 Matthias Feurer , Katharina Eggensperger , Edward Bergman , Florian Pfisterer , Bernd Bischl , Frank Hutter

Gradient methods have become mainstream techniques for Bi-Level Optimization (BLO) in learning and vision fields. The validity of existing works heavily relies on solving a series of approximation subproblems with extraordinarily high…

Optimization and Control · Mathematics 2022-05-23 Risheng Liu , Xuan Liu , Wei Yao , Shangzhi Zeng , Jin Zhang

In (Franceschi et al., 2018) we proposed a unified mathematical framework, grounded on bilevel programming, that encompasses gradient-based hyperparameter optimization and meta-learning. We formulated an approximate version of the problem…

Mathematical Software · Computer Science 2018-06-15 Luca Franceschi , Riccardo Grazzi , Massimiliano Pontil , Saverio Salzo , Paolo Frasconi

This paper presents a comprehensive review of techniques proposed in the literature for solving bilevel optimization problems encountered in various real-life applications. Bilevel optimization is an appropriate choice for hierarchical…

Optimization and Control · Mathematics 2025-11-06 Dhaval Pujara , Ankur Sinha

Deep learning techniques play an increasingly important role in industrial and research environments due to their outstanding results. However, the large number of hyper-parameters to be set may lead to errors if they are set manually. The…

Machine Learning · Computer Science 2020-06-04 Michele Fraccaroli , Evelina Lamma , Fabrizio Riguzzi

There is a clear need for efficient algorithms to tune hyperparameters for statistical learning schemes, since the commonly applied search methods (such as grid search with N-fold cross-validation) are inefficient and/or approximate.…

Machine Learning · Computer Science 2020-04-07 Luis Miguel Lopez-Ramos , Baltasar Beferull-Lozano

We study a general class of bilevel problems, consisting in the minimization of an upper-level objective which depends on the solution to a parametric fixed-point equation. Important instances arising in machine learning include…

Machine Learning · Statistics 2020-07-13 Riccardo Grazzi , Luca Franceschi , Massimiliano Pontil , Saverio Salzo

DPO (Direct Preference Optimization) has become a widely used offline preference optimization algorithm due to its simplicity and training stability. However, DPO is prone to overfitting and collapse. To address these challenges, we propose…

Machine Learning · Computer Science 2025-08-26 Rui Wang , Qianguo Sun , Chao Song , Junlong Wu , Tianrong Chen , Zhiyun Zeng , Yu Li

Various tasks in data science are modeled utilizing the variational regularization approach, where manually selecting regularization parameters presents a challenge. The difficulty gets exacerbated when employing regularizers involving a…

Optimization and Control · Mathematics 2025-07-08 Mohammad Sadegh Salehi , Subhadip Mukherjee , Lindon Roberts , Matthias J. Ehrhardt
‹ Prev 1 3 4 5 6 7 10 Next ›