English
Related papers

Related papers: PMGDA: A Preference-based Multiple Gradient Descen…

200 papers

Multiobjective combinatorial optimization (MOCO) problems can be found in many real-world applications. However, exactly solving these problems would be very challenging, particularly when they are NP-hard. Many handcrafted heuristic…

Machine Learning · Computer Science 2022-05-10 Xi Lin , Zhiyuan Yang , Qingfu Zhang

Reinforcement Learning from Human Feedback (RLHF) has emerged as a powerful technique for aligning large language models (LLMs) with human preferences. However, effectively aligning LLMs with diverse human preferences remains a significant…

Computation and Language · Computer Science 2025-07-03 Chengao Li , Hanyu Zhang , Yunkun Xu , Hongyan Xue , Xiang Ao , Qing He

Post-training of LLMs with RLHF, and subsequently preference optimization algorithms such as DPO, IPO, etc., made a big difference in improving human alignment. However, all such techniques can only work with a single (human) objective. In…

Machine Learning · Computer Science 2025-05-19 Akhil Agnihotri , Rahul Jain , Deepak Ramachandran , Zheng Wen

Optimization of conflicting functions is of paramount importance in decision making, and real world applications frequently involve data that is uncertain or unknown, resulting in multi-objective optimization (MOO) problems of stochastic…

Numerical Analysis · Mathematics 2021-02-08 Suyun Liu , Luis Nunes Vicente

To date, the multi-objective optimization literature has mainly focused on conflicting objectives, studying the Pareto front, or requiring users to balance tradeoffs. Yet, in machine learning practice, there are many scenarios where such…

Machine Learning · Computer Science 2025-03-05 Yonathan Efroni , Ben Kretzu , Daniel Jiang , Jalaj Bhandari , Zheqing , Zhu , Karen Ullrich

Preference disaggregation analysis (PDA) is a widely used approach in multicriteria decision analysis that aims to extract preferential information from holistic judgments provided by decision makers. This paper presents an original…

Optimization and Control · Mathematics 2025-12-09 Betania S. C. Campello , Sarah BenAmor , Leonardo T. Duarte , João Marcos Travassos Romano

Multimodal learning methods with targeted unimodal learning objectives have exhibited their superior efficacy in alleviating the imbalanced multimodal learning problem. However, in this paper, we identify the previously ignored gradient…

Computer Vision and Pattern Recognition · Computer Science 2024-05-29 Yake Wei , Di Hu

When a robot autonomously performs a complex task, it frequently must balance competing objectives while maintaining safety. This becomes more difficult in uncertain environments with stochastic outcomes. Enhancing transparency in the…

Robotics · Computer Science 2024-06-19 Peter Amorese , Shohei Wakayama , Nisar Ahmed , Morteza Lahijanian

In classic reinforcement learning (RL) and decision making problems, policies are evaluated with respect to a scalar reward function, and all optimal policies are the same with regards to their expected return. However, many real-world…

Machine Learning · Computer Science 2023-11-02 Han Shao , Lee Cohen , Avrim Blum , Yishay Mansour , Aadirupa Saha , Matthew R. Walter

There are a lot of real-world black-box optimization problems that need to optimize multiple criteria simultaneously. However, in a multi-objective optimization (MOO) problem, identifying the whole Pareto front requires the prohibitive…

Machine Learning · Computer Science 2023-11-23 Ryota Ozaki , Kazuki Ishikawa , Youhei Kanzaki , Shinya Suzuki , Shion Takeno , Ichiro Takeuchi , Masayuki Karasuyama

Multi-Objective Alignment (MOA) aims to align LLMs' responses with multiple human preference objectives, with Direct Preference Optimization (DPO) emerging as a prominent approach. However, we find that DPO-based MOA approaches suffer from…

Machine Learning · Computer Science 2025-12-09 Moxin Li , Yuantao Zhang , Wenjie Wang , Wentao Shi , Zhuo Liu , Fuli Feng , Tat-Seng Chua

Deep learning models form one of the most powerful machine learning models for the extraction of important features. Most of the designs of deep neural models, i.e., the initialization of parameters, are still manually tuned. Hence,…

Machine Learning · Computer Science 2023-05-18 Mrittika Chakraborty , Wreetbhas Pal , Sanghamitra Bandyopadhyay , Ujjwal Maulik

Current methods for large language model alignment typically use scalar human preference labels. However, this convention tends to oversimplify the multi-dimensional and heterogeneous nature of human preferences, leading to reduced…

Computation and Language · Computer Science 2024-05-24 Yifan Zhong , Chengdong Ma , Xiaoyuan Zhang , Ziran Yang , Haojun Chen , Qingfu Zhang , Siyuan Qi , Yaodong Yang

Multi-task learning is a powerful method for solving multiple correlated tasks simultaneously. However, it is often impossible to find one single solution to optimize all the tasks, since different tasks might conflict with each other.…

Machine Learning · Computer Science 2020-01-01 Xi Lin , Hui-Ling Zhen , Zhenhua Li , Qingfu Zhang , Sam Kwong

Multi-task learning solves multiple correlated tasks. However, conflicts may exist between them. In such circumstances, a single solution can rarely optimize all the tasks, leading to performance trade-offs. To arrive at a set of optimized…

Artificial Intelligence · Computer Science 2024-03-26 Lu Bai , Abhishek Gupta , Yew-Soon Ong

Multi-objective re-ranking has become a critical component of modern multi-stage recommender systems, as it tasked to balance multiple conflicting objectives such as accuracy, diversity, and fairness. Existing multi-objective re-ranking…

Information Retrieval · Computer Science 2026-03-24 Wei Zhou , Wuyang Li , Junkai Ji , Xueliang Li , Wenjing Hong , Zexuan Zhu , Xing Tang , Xiuqiang He

Multi-objective preference alignment of large language models (LLMs) is critical for developing AI systems that are more configurable, personalizable, helpful, and safe. However, optimizing model outputs to satisfy diverse objectives with…

Computation and Language · Computer Science 2025-03-04 Raghav Gupta , Ryan Sullivan , Yunxuan Li , Samrat Phatale , Abhinav Rastogi

Multi-objective multi-armed bandit (MO-MAB) problems traditionally aim to achieve Pareto optimality. However, real-world scenarios often involve users with varying preferences across objectives, resulting in a Pareto-optimal arm that may…

Machine Learning · Computer Science 2025-11-18 Linfeng Cao , Ming Shi , Ness B. Shroff

An important challenge in multi-objective reinforcement learning is obtaining a Pareto front of policies to attain optimal performance under different preferences. We introduce Iterated Pareto Referent Optimisation (IPRO), which decomposes…

Machine Learning · Computer Science 2025-02-07 Willem Röpke , Mathieu Reymond , Patrick Mannion , Diederik M. Roijers , Ann Nowé , Roxana Rădulescu

Multi-objective optimization is central to many engineering and machine learning applications, where multiple objectives must be optimized in balance. While multi-gradient based optimization methods combine these objectives in each step,…

Optimization and Control · Mathematics 2026-05-13 Trang H. Tran , Luis Nunes Vicente