Related papers: Aligned Multi Objective Optimization

Aligned Multi Objective Optimization

URL: http://arxiv.org/abs/2502.14096v1
Date: Wed, 19 Feb 2025 20:50:03 GMT
Title: Aligned Multi Objective Optimization
Authors: Yonathan Efroni, Ben Kertzu, Daniel Jiang, Jalaj Bhandari, Zheqing, Zhu, Karen Ullrich,
Abstract summary: 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. We introduce the Aligned Multi-Objective Optimization framework, propose new algorithms for this setting, and provide theoretical guarantees of their superior performance.
Score: 14.320569438197271
License:
Abstract: 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.

Related papers

Rethinking Multi-Objective Learning through Goal-Conditioned Supervised Learning [8.593384839118658]
Multi-objective learning aims to optimize multiple objectives simultaneously with a single model. It suffers from the difficulty to formalize and conduct the exact learning process. We propose a general framework for automatically learning to achieve multiple objectives based on the existing sequential data.
arXiv Detail & Related papers (2024-12-12T03:47:40Z)
Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate [105.86576388991713]
We introduce a normalized gradient difference (NGDiff) algorithm, enabling us to have better control over the trade-off between the objectives. We provide a theoretical analysis and empirically demonstrate the superior performance of NGDiff among state-of-the-art unlearning methods on the TOFU and MUSE datasets.
arXiv Detail & Related papers (2024-10-29T14:41:44Z)
Deep Pareto Reinforcement Learning for Multi-Objective Recommender Systems [60.91599969408029]
optimizing multiple objectives simultaneously is an important task for recommendation platforms. Existing multi-objective recommender systems do not systematically consider such dynamic relationships.
arXiv Detail & Related papers (2024-07-04T02:19:49Z)
Hierarchical Optimization-Derived Learning [58.69200830655009]
We establish a new framework, named Hierarchical ODL (HODL), to simultaneously investigate the intrinsic behaviors of optimization-derived model construction and its corresponding learning process. This is the first theoretical guarantee for these two coupled ODL components: optimization and learning.
arXiv Detail & Related papers (2023-02-11T03:35:13Z)
A Scale-Independent Multi-Objective Reinforcement Learning with Convergence Analysis [0.6091702876917281]
Many sequential decision-making problems need optimization of different objectives which possibly conflict with each other. We develop a single-agent scale-independent multi-objective reinforcement learning on the basis of the Advantage Actor-Critic (A2C) algorithm. A convergence analysis is then done for the devised multi-objective algorithm providing a convergence-in-mean guarantee.
arXiv Detail & Related papers (2023-02-08T16:38:55Z)
Joint Training of Deep Ensembles Fails Due to Learner Collusion [61.557412796012535]
Ensembles of machine learning models have been well established as a powerful method of improving performance over a single model. Traditionally, ensembling algorithms train their base learners independently or sequentially with the goal of optimizing their joint performance. We show that directly minimizing the loss of the ensemble appears to rarely be applied in practice.
arXiv Detail & Related papers (2023-01-26T18:58:07Z)
Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach [38.76462300149459]
We develop a Multi-objective Correction (MoCo) method for multi-objective gradient optimization. The unique feature of our method is that it can guarantee convergence without increasing the non fairness gradient.
arXiv Detail & Related papers (2022-10-23T05:54:26Z)
A Field Guide to Federated Optimization [161.3779046812383]
Federated learning and analytics are a distributed approach for collaboratively learning models (or statistics) from decentralized data. This paper provides recommendations and guidelines on formulating, designing, evaluating and analyzing federated optimization algorithms.
arXiv Detail & Related papers (2021-07-14T18:09:08Z)
A Distributional View on Multi-Objective Policy Optimization [24.690800846837273]
We propose an algorithm for multi-objective reinforcement learning that enables setting desired preferences for objectives in a scale-invariant way. We show that setting different preferences in our framework allows us to trace out the space of nondominated solutions.
arXiv Detail & Related papers (2020-05-15T13:02:17Z)
Multi-Task Learning for Dense Prediction Tasks: A Survey [87.66280582034838]
Multi-task learning (MTL) techniques have shown promising results w.r.t. performance, computations and/or memory footprint. We provide a well-rounded view on state-of-the-art deep learning approaches for MTL in computer vision.
arXiv Detail & Related papers (2020-04-28T09:15:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.