English
Related papers

Related papers: Preference-based optimization from noisy pairwise …

200 papers

We propose a novel continuous-time algorithm for inequality-constrained convex optimization inspired by proportional-integral control. Unlike the popular primal-dual gradient dynamics, our method includes a proportional term to control the…

Optimization and Control · Mathematics 2024-09-12 V. Cerone , S. M. Fosson , S. Pirrera , D. Regruto

Incorporating user preferences into multi-objective Bayesian optimization (MOBO) allows for personalization of the optimization procedure. Preferences are often abstracted in the form of an unknown utility function, estimated through…

Machine Learning · Computer Science 2025-03-19 Joshua Hang Sai Ip , Ankush Chakrabarty , Ali Mesbah , Diego Romeres

In this work, we study optimization specified only through a comparison oracle: given two points, it reports which one is preferred. We call it function-free optimization because we do not assume access to, nor the existence of, a canonical…

Optimization and Control · Mathematics 2026-05-20 Katya Scheinberg , Zikai Xiong

In this paper, we propose an active learning algorithm and models which can gradually learn individual's preference through pairwise comparisons. The active learning scheme aims at finding individual's most preferred choice with minimized…

Machine Learning · Statistics 2018-05-07 Jie Yang , Diego Klabjan

We propose and analyze a sequential quadratic programming algorithm for minimizing a noisy nonlinear smooth function subject to noisy nonlinear smooth equality constraints. The algorithm uses a step decomposition strategy and, as a result,…

Optimization and Control · Mathematics 2025-03-11 Albert S. Berahas , Jiahao Shi , Baoyu Zhou

In this paper, we present a stochastic gradient algorithm for minimizing a smooth objective function that is an expectation over noisy cost samples, and only the latter are observed for any given parameter. Our algorithm employs a gradient…

Optimization and Control · Mathematics 2023-07-03 Akash Mondal , Prashanth L. A. , Shalabh Bhatnagar

Margin-based optimization is fundamental to improving generalization and robustness in classification tasks. In the context of reward model learning from preferences within Reinforcement Learning from Human Feedback (RLHF), existing methods…

Machine Learning · Computer Science 2025-12-02 Yaswanth Chittepu , Prasann Singhal , Greg Durrett , Scott Niekum

We consider Bayesian optimization of an expensive-to-evaluate black-box objective function, where we also have access to cheaper approximations of the objective. In general, such approximations arise in applications such as reinforcement…

Machine Learning · Statistics 2016-11-16 Matthias Poloczek , Jialei Wang , Peter I. Frazier

We propose a novel sparse preference learning/ranking algorithm. Our algorithm approximates the true utility function by a weighted sum of basis functions using the squared loss on pairs of data points, and is a generalization of the kernel…

Machine Learning · Statistics 2013-07-04 Evgeni Tsivtsivadze , Tom Heskes

We study the problem of learning to rank from pairwise preferences, and solve a long-standing open problem that has led to development of many heuristics but no provable results for our particular problem. Given a set $V$ of $n$ elements,…

Data Structures and Algorithms · Computer Science 2011-05-18 Nir Ailon

Practitioners commonly align large language models using pairwise preferences, i.e., given labels of the type response A is preferred to response B for a given input. Perhaps less commonly, methods have also been developed for binary…

Computation and Language · Computer Science 2024-04-24 Jing Xu , Andrew Lee , Sainbayar Sukhbaatar , Jason Weston

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

Decentralized optimization is typically studied under the assumption of noise-free transmission. However, real-world scenarios often involve the presence of noise due to factors such as additive white Gaussian noise channels or…

Optimization and Control · Mathematics 2023-07-28 Suhail M. Shah , Raghu Bollapragada

Preference optimization techniques, such as Direct Preference Optimization (DPO), are frequently employed to enhance the reasoning capabilities of large language models (LLMs) in domains like mathematical reasoning and coding, typically…

Computation and Language · Computer Science 2025-02-17 Fangkai Jiao , Geyang Guo , Xingxing Zhang , Nancy F. Chen , Shafiq Joty , Furu Wei

We propose a novel and efficient algorithm for the collaborative preference completion problem, which involves jointly estimating individualized rankings for a set of entities over a shared set of items, based on a limited number of…

Machine Learning · Statistics 2016-11-16 Suriya Gunasekar , Oluwasanmi Koyejo , Joydeep Ghosh

Discrete optimization problems often arise in deep learning tasks, despite the fact that neural networks typically operate on continuous data. One class of these problems involve objective functions which depend on neural networks, but…

Machine Learning · Computer Science 2023-10-17 Eric Lei , Arman Adibi , Hamed Hassani

Large-scale optimization problems that seek sparse solutions have become ubiquitous. They are routinely solved with various specialized first-order methods. Although such methods are often fast, they usually struggle with not-so-well…

Optimization and Control · Mathematics 2021-11-29 Valentina De Simone , Daniela di Serafino , Jacek Gondzio , Spyridon Pougkakiotis , Marco Viola

While astonishingly capable, large Language Models (LLM) can sometimes produce outputs that deviate from human expectations. Such deviations necessitate an alignment phase to prevent disseminating untruthful, toxic, or biased information.…

Artificial Intelligence · Computer Science 2024-10-30 Long Tan Le , Han Shu , Tung-Anh Nguyen , Choong Seon Hong , Nguyen H. Tran

Learning from implicit feedback is challenging because of the difficult nature of the one-class problem: we can observe only positive examples. Most conventional methods use a pairwise ranking approach and negative samplers to cope with the…

Machine Learning · Computer Science 2021-05-12 Riku Togashi , Masahiro Kato , Mayu Otani , Tetsuya Sakai , Shin'ichi Satoh

Decisions under uncertainty or with multiple objectives usually require the decision maker to formulate a preference regarding risks or trade-offs. If this preference is known, the ordered weighted averaging (OWA) criterion can be applied…

Optimization and Control · Mathematics 2023-08-02 Werner Baak , Marc Goerigk , Michael Hartisch