Interactive Pareto navigation for deep multi-task learning

• URL: http://arxiv.org/abs/2606.19521v1
• Date: Wed, 17 Jun 2026 19:08:37 GMT
• Title: Interactive Pareto navigation for deep multi-task learning
• Abstract summary: In multi-task learning, handling an increasing number of objectives can quickly become challenging.<n>A widely used approach is thus to aggregate the individual losses in a single loss function by a weighted sum.<n>This often fails to capture either the decision maker's preferences or multiple adjustments and computations which becomes prohibitively expensive in deep learning applications.
• Score: 0.764671395172401
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: In multi-task learning, handling an increasing number of objectives can quickly become challenging, both in terms of the computational resources and the decision maker's capacity to choose appropriate trade-offs. A widely used approach is thus to aggregate the individual losses in a single loss function by a weighted sum. This often fails to capture either the decision maker's preferences as a result of the shape of the Pareto front, or requires multiple adjustments and computations which becomes prohibitively expensive in deep learning applications. To address these issues, we introduce a novel framework, Preference Pareto Exploration (PPE), which enforces the decision maker's preferences while accounting for the geometry of the Pareto set in an interactive exploration process. PPE is based on a predictor-corrector method that performs predictor steps tangential to the manifold of Pareto-optimal solutions, following the decision maker's preference. The subsequent corrector step results in a new trade-off reflecting this preference. To avoid explicit Hessian computations when characterizing the tangent space of the manifold, we employ a Krylov subspace method that relies solely on matrix-vector products. These products can be efficiently obtained via automatic differentiation, ensuring both efficiency and robustness throughout the optimization process. The method's functionality and performance are demonstrated using both toy problems and examples from deep learning.

Related papers

• Self-Supervised Penalty-Based Learning for Robust Constrained Optimization [4.297070083645049]
  We propose a new methodology for parameterized constrained robust optimization, based on learning with a self-supervised penalty-based loss function.<n>Our approach is able to effectively learn neural network approximations whose inference time is significantly smaller than the time of traditional solvers.
  arXiv  Detail & Related papers  (2025-03-07T06:42:17Z)
• Towards Efficient Pareto Set Approximation via Mixture of Experts Based Model Fusion [53.33473557562837]
  Solving multi-objective optimization problems for large deep neural networks is a challenging task due to the complexity of the loss landscape and the expensive computational cost. We propose a practical and scalable approach to solve this problem via mixture of experts (MoE) based model fusion. By ensembling the weights of specialized single-task models, the MoE module can effectively capture the trade-offs between multiple objectives.
  arXiv  Detail & Related papers  (2024-06-14T07:16:18Z)
• MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation [80.47072100963017]
  We introduce a novel and low-compute algorithm, Model Merging with Amortized Pareto Front (MAP)<n>MAP efficiently identifies a set of scaling coefficients for merging multiple models, reflecting the trade-offs involved.<n>We also introduce Bayesian MAP for scenarios with a relatively low number of tasks and Nested MAP for situations with a high number of tasks, further reducing the computational cost of evaluation.
  arXiv  Detail & Related papers  (2024-06-11T17:55:25Z)
• UCB-driven Utility Function Search for Multi-objective Reinforcement Learning [51.00436121587591]
  In Multi-objective Reinforcement Learning (MORL) agents are tasked with optimising decision-making behaviours.<n>We focus on the case of linear utility functions parametrised by weight vectors w.<n>We introduce a method based on Upper Confidence Bound to efficiently search for the most promising weight vectors during different stages of the learning process.
  arXiv  Detail & Related papers  (2024-05-01T09:34:42Z)
• PMGDA: A Preference-based Multiple Gradient Descent Algorithm [12.600588000788214]
  It is desirable in many multi-objective machine learning applications, such as multi-task learning, to find a solution that fits a given preference of a decision maker. This paper proposes a novel predict-and-correct framework for locating a solution that fits the preference of a decision maker.
  arXiv  Detail & Related papers  (2024-02-14T11:27:31Z)
• Data-Efficient Interactive Multi-Objective Optimization Using ParEGO [6.042269506496206]
  Multi-objective optimization seeks to identify a set of non-dominated solutions that provide optimal trade-offs among competing objectives. In practical applications, decision-makers (DMs) will select a single solution that aligns with their preferences to be implemented. We propose two novel algorithms that efficiently locate the most preferred region of the Pareto front in expensive-to-evaluate problems.
  arXiv  Detail & Related papers  (2024-01-12T15:55:51Z)
• Backpropagation of Unrolled Solvers with Folded Optimization [55.04219793298687]
  The integration of constrained optimization models as components in deep networks has led to promising advances on many specialized learning tasks. One typical strategy is algorithm unrolling, which relies on automatic differentiation through the operations of an iterative solver. This paper provides theoretical insights into the backward pass of unrolled optimization, leading to a system for generating efficiently solvable analytical models of backpropagation.
  arXiv  Detail & Related papers  (2023-01-28T01:50:42Z)
• Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Problems by Reinforcement Learning [52.74071439183113]
  We study the predict-then-optimize framework in the context of sequential decision problems (formulated as MDPs) solved via reinforcement learning. Two significant computational challenges arise in applying decision-focused learning to MDPs.
  arXiv  Detail & Related papers  (2021-06-06T23:53:31Z)
• Multi-Objective Learning to Predict Pareto Fronts Using Hypervolume Maximization [0.0]
  Real-world problems are often multi-objective with decision-makers unable to specify a priori which trade-off between the conflicting objectives is preferable. We propose a novel learning approach to estimate the Pareto front by maximizing the dominated hypervolume (HV) of the average loss vectors corresponding to a set of learners. In our approach, the set of learners are trained multi-objectively with a dynamic loss function, wherein each learner's losses are weighted by their HV maximizing gradients. Experiments on three different multi-objective tasks show that the outputs of the set of learners are indeed well-spread on
  arXiv  Detail & Related papers  (2021-02-08T20:41:21Z)
• Learning with Differentiable Perturbed Optimizers [54.351317101356614]
  We propose a systematic method to transform operations into operations that are differentiable and never locally constant. Our approach relies on perturbeds, and can be used readily together with existing solvers. We show how this framework can be connected to a family of losses developed in structured prediction, and give theoretical guarantees for their use in learning tasks.
  arXiv  Detail & Related papers  (2020-02-20T11:11:32Z)

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.