Aligned Multi Objective Optimization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913717642330112 |
|---|---|
| author | Efroni, Yonathan Kretzu, Ben Jiang, Daniel Bhandari, Jalaj Zheqing Zhu Ullrich, Karen |
| author_facet | Efroni, Yonathan Kretzu, Ben Jiang, Daniel Bhandari, Jalaj Zheqing Zhu Ullrich, Karen |
| contents | 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 conflict does not take place. Recent findings from multi-task learning, reinforcement learning, and LLMs training show that diverse related tasks can enhance performance across objectives simultaneously. Despite this evidence, such phenomenon has not been examined from an optimization perspective. This leads to a lack of generic gradient-based methods that can scale to scenarios with a large number of related objectives. To address this gap, we introduce the Aligned Multi-Objective Optimization framework, propose new algorithms for this setting, and provide theoretical guarantees of their superior performance compared to naive approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_14096 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Aligned Multi Objective Optimization Efroni, Yonathan Kretzu, Ben Jiang, Daniel Bhandari, Jalaj Zheqing Zhu Ullrich, Karen Machine Learning Optimization and Control 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 conflict does not take place. Recent findings from multi-task learning, reinforcement learning, and LLMs training show that diverse related tasks can enhance performance across objectives simultaneously. Despite this evidence, such phenomenon has not been examined from an optimization perspective. This leads to a lack of generic gradient-based methods that can scale to scenarios with a large number of related objectives. To address this gap, we introduce the Aligned Multi-Objective Optimization framework, propose new algorithms for this setting, and provide theoretical guarantees of their superior performance compared to naive approaches. |
| title | Aligned Multi Objective Optimization |
| topic | Machine Learning Optimization and Control |
| url | https://arxiv.org/abs/2502.14096 |