English
Related papers

Related papers: Model-Based Derivative-Free Optimization Methods a…

200 papers

We introduce a general framework for large-scale model-based derivative-free optimization based on iterative minimization within random subspaces. We present a probabilistic worst-case complexity analysis for our method, where in particular…

Optimization and Control · Mathematics 2021-02-25 Coralia Cartis , Lindon Roberts

We introduce a novel framework for decentralized projection-free optimization, extending projection-free methods to a broader class of upper-linearizable functions. Our approach leverages decentralized optimization techniques with the…

Optimization and Control · Mathematics 2026-02-25 Yiyang Lu , Mohammad Pedramfar , Vaneet Aggarwal

Aligning large language models (LLMs) with human values and intentions is crucial for their utility, honesty, and safety. Reinforcement learning from human feedback (RLHF) is a popular approach to achieve this alignment, but it faces…

Machine Learning · Computer Science 2025-07-22 Junkang Wu , Xue Wang , Zhengyi Yang , Jiancan Wu , Jinyang Gao , Bolin Ding , Xiang Wang , Xiangnan He

Many computational problems involve optimization over discrete variables with quadratic interactions. Known as discrete quadratic models (DQMs), these problems in general are NP-hard. Accordingly, there is increasing interest in encoding…

Quantum Physics · Physics 2024-02-16 Tristan Zaborniak , Ulrike Stege

Recent deep reinforcement learning methods have achieved remarkable success in solving multi-objective combinatorial optimization problems (MOCOPs) by decomposing them into multiple subproblems, each associated with a specific weight…

Artificial Intelligence · Computer Science 2026-03-23 Mingfeng Fan , Jianan Zhou , Yifeng Zhang , Yaoxin Wu , Jinbiao Chen , Guillaume Adrien Sartoretti

Reference-free preference optimization has emerged as an efficient alternative to reinforcement learning from human feedback, with Simple Preference Optimization(SimPO) demonstrating strong performance by eliminating the explicit reference…

Machine Learning · Computer Science 2026-05-13 Zhengyuan Fan , Zhonghua Wu , Yuxuan Du , Qun Chen

The superiorization methodology is intended to work with input data of constrained minimization problems, that is, a target function and a set of constraints. However, it is based on an antipodal way of thinking to what leads to constrained…

Optimization and Control · Mathematics 2020-10-26 Yair Censor , Edgar Garduño , Elias S. Helou , Gabor T. Herman

Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). However, neither RLHF nor DPO take into account the fact that learning certain…

Computer Vision and Pattern Recognition · Computer Science 2026-02-16 Florinel-Alin Croitoru , Vlad Hondru , Radu Tudor Ionescu , Nicu Sebe , Mubarak Shah

Differentiable optimization has attracted significant research interest, particularly for quadratic programming (QP). Existing approaches for differentiating the solution of a QP with respect to its defining parameters often rely on…

Machine Learning · Computer Science 2025-10-31 Connor W. Magoon , Fengyu Yang , Noam Aigerman , Shahar Z. Kovalsky

Reinforcement learning from human feedback (RLHF) plays a crucial role in aligning language models with human preferences. While the significance of dataset quality is generally recognized, explicit investigations into its impact within the…

Machine Learning · Computer Science 2024-12-04 Tetsuro Morimura , Mitsuki Sakamoto , Yuu Jinnai , Kenshi Abe , Kaito Ariu

Reinforcement learning from human feedback (RLHF) and direct preference optimization (DPO) are important techniques to align large language models (LLM) with human preference. However, the quality of RLHF and DPO training is seriously…

Machine Learning · Computer Science 2025-12-10 Ziyi Chen , Junyi Li , Peiran Yu , Heng Huang

Data-driven decision-making processes increasingly utilize end-to-end learnable deep neural networks to render final decisions. Sometimes, the output of the forward functions in certain layers is determined by the solutions to mathematical…

Machine Learning · Computer Science 2024-12-31 Jianming Pan , Zeqi Ye , Xiao Yang , Xu Yang , Weiqing Liu , Lewen Wang , Jiang Bian

Computational design problems arise in a number of settings, from synthetic biology to computer architectures. In this paper, we aim to solve data-driven model-based optimization (MBO) problems, where the goal is to find a design input that…

Machine Learning · Computer Science 2021-07-15 Brandon Trabucco , Aviral Kumar , Xinyang Geng , Sergey Levine

We present a model-based derivative-free method for optimization subject to general convex constraints, which we assume are unrelaxable and accessed only through a projection operator that is cheap to evaluate. We prove global convergence…

Optimization and Control · Mathematics 2022-03-18 Matthew Hough , Lindon Roberts

Data-based optimization (DBO) offers a promising approach for efficiently optimizing shape for better aerodynamic performance by leveraging a pretrained surrogate model for offline evaluations during iterations. However, DBO heavily relies…

Machine Learning · Computer Science 2026-03-31 Yunjia Yang , Runze Li , Yufei Zhang , Haixin Chen

Derivative-free optimization methods are numerical methods for optimization problems in which no derivative information is used. Such optimization problems are widely seen in many real applications. One particular class of derivative-free…

Optimization and Control · Mathematics 2023-02-24 Pengcheng Xie , Ya-xiang Yuan

any practical multiobjective optimization (MOO) problems include discrete decision variables and/or nonlinear model equations and exhibit disconnected or smooth but nonconvex Pareto surfaces. Scalarization methods, such as the weighted-sum…

Optimization and Control · Mathematics 2024-10-23 Ye Seol Lee , George Jackson , Amparo Galindo , Claire S. Adjiman

We present approximation theories and efficient training methods for derivative-informed Fourier neural operators (DIFNOs) with applications to PDE-constrained optimization. A DIFNO is an FNO trained by minimizing its prediction error…

Machine Learning · Computer Science 2026-03-17 Boyuan Yao , Dingcheng Luo , Lianghao Cao , Nikola Kovachki , Thomas O'Leary-Roseberry , Omar Ghattas

The aim of this PhD project is to develop fast and robust reasoning tools for dependency quantified Boolean formulas (DQBF). In this paper, we outline two properties, autarkies and symmetries, that potentially can be exploited for pre- and…

Logic in Computer Science · Computer Science 2019-10-04 Ankit Shukla

Prompt Optimization has emerged as a crucial approach due to its capabilities in steering Large Language Models to solve various tasks. However, current works mainly rely on the random rewriting ability of LLMs, and the optimization process…

Computation and Language · Computer Science 2025-10-22 Tao Tao , Guanghui Zhu , Lang Guo , Hongyi Chen , Chunfeng Yuan , Yihua Huang