Solving Few-Shot Multiobjective Multitask Optimization via Iterative Sequential Transfer

• URL: http://arxiv.org/abs/2609.11228v1
• Date: Thu, 10 Sep 2026 08:28:28 GMT
• Title: Solving Few-Shot Multiobjective Multitask Optimization via Iterative Sequential Transfer
• Abstract summary: This paper introduces Iterative Sequential Transfer (IST) to solve multitask optimization problems.<n>We propose a likelihood-informed task prioritization mechanism to maximize transfer utility.<n> Empirical results on benchmark and real-world problems verify the effectiveness of the proposed method under tight budgets.
• Score: 28.698139321250906
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Applying knowledge transfer across multiple optimization tasks, multitask optimization (MTO) emerges as a promising approach to solving synergistic optimization tasks simultaneously. However, the development of effective knowledge transfer mechanisms in MTO fundamentally relies on aligning elite solution distributions across tasks. This dependency creates a critical bottleneck in few-shot optimization regimes, as restricted evaluation budgets impede the identification of elite solution distributions required for beneficial transfer. This challenge is exacerbated in multiobjective multitask problems, where each optimizer must approximate a continuous Pareto manifold rather than a single optimal point. This paper introduces Iterative Sequential Transfer (IST) to circumvent this bottleneck. We model MTO as a sequence of sequential transfer optimization problems, concentrating evaluations on a single target per iteration. We propose a likelihood-informed task prioritization mechanism to maximize transfer utility by identifying the task most likely ready for knowledge integration. Empirical results on benchmark and real-world problems verify the effectiveness of the proposed method under tight budgets.

Related papers

• Delve into the Applicability of Advanced Optimizers for Multi-Task Learning [70.80216936064654]
  Multi-Task Learning (MTL) is a machine learning problem that has seen extensive development over the past decade.<n>We propose APT (Applicability of advanced oPizers), a framework featuring a simple adaptive momentum mechanism designed to balance the strengths between advanceds and MTL.
  arXiv  Detail & Related papers  (2026-04-10T04:15:31Z)
• Parametric Expensive Multi-Objective Optimization via Generative Solution Modeling [34.344228998247225]
  This paper introduces the first parametric multi-objective Bayesian that learns this inverse model by alternating between acquisition-driven search and generative models.<n>We theoretically justify the faster convergence by leveraging inter-task synergies through task-aware Gaussian processes.
  arXiv  Detail & Related papers  (2025-11-12T15:13:27Z)
• A Unified Multi-Task Learning Framework for Generative Auto-Bidding with Validation-Aligned Optimization [51.27959658504722]
  Multi-task learning offers a principled framework to train these tasks jointly through shared representations.<n>Existing multi-task optimization strategies are primarily guided by training dynamics and often generalize poorly in volatile bidding environments.<n>We present Validation-Aligned Multi-task Optimization (VAMO), which adaptively assigns task weights based on the alignment between per-task training gradients and a held-out validation gradient.
  arXiv  Detail & Related papers  (2025-10-09T03:59:51Z)
• Continual Optimization with Symmetry Teleportation for Multi-Task Learning [73.28772872740744]
  Multi-task learning (MTL) enables the simultaneous learning of multiple tasks using a single model.<n>We propose a novel approach based on Continual Optimization with Symmetry Teleportation (COST)<n>COST seeks an alternative loss-equivalent point on the loss landscape to reduce conflict gradients.
  arXiv  Detail & Related papers  (2025-03-06T02:58:09Z)
• Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System [75.25394449773052]
  Large Language Model (LLM) based multi-agent systems (MAS) show remarkable potential in collaborative problem-solving.<n>Yet they still face critical challenges: low communication efficiency, poor scalability, and a lack of effective parameter-updating optimization methods.<n>We present Optima, a novel framework that addresses these issues by significantly enhancing both communication efficiency and task effectiveness.
  arXiv  Detail & Related papers  (2024-10-10T17:00:06Z)
• Multi-Fidelity Bayesian Optimization With Across-Task Transferable Max-Value Entropy Search [36.14499894307206]
  This paper introduces a novel information-theoretic acquisition function that balances the need to acquire information about the current task with the goal of collecting information transferable to future tasks.<n>Results show that the proposed acquisition strategy can significantly improve the optimization efficiency as soon as a sufficient number of tasks is processed.
  arXiv  Detail & Related papers  (2024-03-14T17:00:01Z)
• Towards Multi-Objective High-Dimensional Feature Selection via Evolutionary Multitasking [63.91518180604101]
  This paper develops a novel EMT framework for high-dimensional feature selection problems, namely MO-FSEMT. A task-specific knowledge transfer mechanism is designed to leverage the advantage information of each task, enabling the discovery and effective transmission of high-quality solutions.
  arXiv  Detail & Related papers  (2024-01-03T06:34:39Z)
• Bayesian Inverse Transfer in Evolutionary Multiobjective Optimization [29.580786235313987]
  We introduce the first Inverse Transfer Multiobjective (invTrEMO) InvTrEMO harnesses the common objective functions in many prevalent areas, even when decision spaces do not precisely align between tasks. InvTrEMO yields high-precision inverse models as a significant byproduct, enabling the generation of tailored solutions on-demand.
  arXiv  Detail & Related papers  (2023-12-22T14:12:18Z)
• Sequential Information Design: Markov Persuasion Process and Its Efficient Reinforcement Learning [156.5667417159582]
  This paper proposes a novel model of sequential information design, namely the Markov persuasion processes (MPPs) Planning in MPPs faces the unique challenge in finding a signaling policy that is simultaneously persuasive to the myopic receivers and inducing the optimal long-term cumulative utilities of the sender. We design a provably efficient no-regret learning algorithm, the Optimism-Pessimism Principle for Persuasion Process (OP4), which features a novel combination of both optimism and pessimism principles.
  arXiv  Detail & Related papers  (2022-02-22T05:41:43Z)
• dMFEA-II: An Adaptive Multifactorial Evolutionary Algorithm for Permutation-based Discrete Optimization Problems [6.943742860591444]
  We propose the first adaptation of the recently introduced Multifactorial Evolutionary Algorithm II (MFEA-II) to permutation-based discrete environments. The performance of the proposed solver has been assessed over 5 different multitasking setups.
  arXiv  Detail & Related papers  (2020-04-14T14:42:47Z)
• Multifactorial Cellular Genetic Algorithm (MFCGA): Algorithmic Design, Performance Comparison and Genetic Transferability Analysis [17.120962133525225]
  Multiobjective optimization is an incipient research area which is lately gaining a notable research momentum. In this work we propose a novel algorithmic scheme for Multifactorial Optimization scenarios. The proposed MFCGA hinges on concepts from Cellular Automata to implement mechanisms for exchanging knowledge among problems.
  arXiv  Detail & Related papers  (2020-03-24T11:03:55Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.