English
Related papers

Related papers: Enhancing finite-difference based derivative-free …

200 papers

Direct Preference Optimization (DPO), which derives reward signals directly from pairwise preference data, has shown its effectiveness on aligning Large Language Models (LLMs) with human preferences. Despite its widespread use across…

Computation and Language · Computer Science 2024-04-09 Duanyu Feng , Bowen Qin , Chen Huang , Zheng Zhang , Wenqiang Lei

Federated learning (FL) has emerged as a powerful paradigm for collaborative model training across distributed clients while preserving data privacy. However, existing FL algorithms predominantly focus on unconstrained optimization problems…

Optimization and Control · Mathematics 2025-08-22 Hongye Wang , Zhaoye Pan , Chang He , Jiaxiang Li , Bo Jiang

In this paper, a new gradient-based optimization approach by automatically adjusting the learning rate is proposed. This approach can be applied to design non-adaptive learning rate and adaptive learning rate. Firstly, I will introduce the…

Machine Learning · Computer Science 2022-07-07 Xin Cao

In many automated planning applications, action costs can be hard to specify. An example is the time needed to travel through a certain road segment, which depends on many factors, such as the current weather conditions. A natural way to…

Artificial Intelligence · Computer Science 2024-08-27 Jayanta Mandi , Marco Foschini , Daniel Holler , Sylvie Thiebaux , Jorg Hoffmann , Tias Guns

This study aims to provide a comprehensive assessment of single-objective and multi-objective optimisation algorithms for the design of an elbow-type draft tube, as well as to introduce a computationally efficient optimisation workflow. The…

Optimization and Control · Mathematics 2024-01-18 Ante Sikirica , Ivana Lučin , Marta Alvir , Lado Kranjčević , Zoran Čarija

We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent.…

Machine Learning · Computer Science 2017-08-29 John Schulman , Filip Wolski , Prafulla Dhariwal , Alec Radford , Oleg Klimov

The performance of policy gradient methods is sensitive to hyperparameter settings that must be tuned for any new application. Widely used grid search methods for tuning hyperparameters are sample inefficient and computationally expensive.…

Machine Learning · Computer Science 2019-09-19 Supratik Paul , Vitaly Kurin , Shimon Whiteson

This paper tackles optimization problems whose objective and constraints involve a trained Neural Network (NN), where the goal is to maximize $f(\Phi(x))$ subject to $c(\Phi(x)) \leq 0$, with $f$ smooth, $c$ general and non-stringent, and…

Optimization and Control · Mathematics 2025-10-03 Pierre-Yves Bouchet , Thibaut Vidal

We design Local LMO - a new projection-free gradient-type method for constrained optimization. The key algorithmic idea is to replace the global linear minimization oracle over the constraint set used by Frank-Wolfe (FW) with a local linear…

Optimization and Control · Mathematics 2026-05-12 Peter Richtárik , Kaja Gruntkowska , Hanmin Li

In this paper, a new sequential surrogate-based optimization (SSBO) algorithm is developed, which aims to improve the global search ability and local search efficiency for the global optimization of expensive black-box models. The proposed…

Machine Learning · Statistics 2018-11-30 Chunlin Gong , Xu Li , Hua Su , Jinlei Guo , Liangxian Gu

Reduced-order modelling and low-dimensional surrogate models generated using machine learning algorithms have been widely applied in high-dimensional dynamical systems to improve the algorithmic efficiency. In this paper, we develop a…

Solving optimization problems with unknown parameters often requires learning a predictive model to predict the values of the unknown parameters and then solving the problem using these values. Recent work has shown that including the…

Machine Learning · Computer Science 2020-10-23 Kai Wang , Bryan Wilder , Andrew Perrault , Milind Tambe

Data-driven evolutionary optimization has witnessed great success in solving complex real-world optimization problems. However, existing data-driven optimization algorithms require that all data are centrally stored, which is not always…

Neural and Evolutionary Computing · Computer Science 2021-02-17 Jinjin Xu , Yaochu Jin , Wenli Du , Sai Gu

Metafeatures, or dataset characteristics, have been shown to improve the performance of hyperparameter optimization (HPO). Conventionally, metafeatures are precomputed and used to measure the similarity between datasets, leading to a better…

Machine Learning · Computer Science 2021-02-09 Hadi S. Jomaa , Lars Schmidt-Thieme , Josif Grabocka

A machine-learning-based framework for modeling the error introduced by surrogate models of parameterized dynamical systems is proposed. The framework entails the use of high-dimensional regression techniques (e.g., random forests, LASSO)…

Numerical Analysis · Computer Science 2017-06-02 Sumeet Trehan , Kevin Carlberg , Louis J. Durlofsky

A new technique of global optimization and its applications in particular to neural networks are presented. The algorithm is also compared to other global optimization algorithms such as Gradient descent (GD), Monte Carlo (MC), Genetic…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-12-18 Homayoun Valafar , Okan K. Ersoy , Faramarz Valafar

We propose derivative-informed neural operators (DINOs), a general family of neural networks to approximate operators as infinite-dimensional mappings from input function spaces to output function spaces or quantities of interest. After…

Numerical Analysis · Mathematics 2023-10-18 Thomas O'Leary-Roseberry , Peng Chen , Umberto Villa , Omar Ghattas

Optimizing the hyperparameters and architecture of a neural network is a long yet necessary phase in the development of any new application. This consuming process can benefit from the elaboration of strategies designed to quickly discard…

Optimization and Control · Mathematics 2021-03-16 Dounia Lakhmiri , Sébastien Le Digabel

The optimization of industrial processes remains a critical challenge, particularly when no mathematical formulation of objective functions or constraints is available. This study addresses this issue by proposing a surrogate-based,…

Computational Engineering, Finance, and Science · Computer Science 2025-07-16 Eider Garate-Perez , Kerman López de Calle-Etxabe , Susana Ferreiro

Distributed optimization is fundamental to modern machine learning applications like federated learning, but existing methods often struggle with ill-conditioned problems and face stability-versus-speed tradeoffs. We introduce fractional…

Machine Learning · Computer Science 2024-12-04 Andrei Lixandru , Marcel van Gerven , Sergio Pequito