Not All Objectives Are Born Equal: Priority-Constrained Descent for Hierarchical Multi-Objective Optimization

• URL: http://arxiv.org/abs/2606.29521v1
• Date: Sun, 28 Jun 2026 17:31:47 GMT
• Title: Not All Objectives Are Born Equal: Priority-Constrained Descent for Hierarchical Multi-Objective Optimization
• Abstract summary: We introduce Priority-Constrained Descent (PCD) to explicitly exploit hierarchical objective structures.<n>PCD preserves the direction of primary descent whilst allowing for the minimal distortion necessary to guarantee progress on secondary objectives.<n>We evaluate PCD within structured network compression settings, unstructured sparsity and low-rankness, and across a variety of synthetic experiments.
• Score: 0.6875312133832079
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep learning problems rarely involve objectives that are equal in importance. A primary objective defines the goal, whilst secondary objectives, such as sparsity, compression, or robustness constrain the solution. While existing multi-objective methods have proven effective in practice, they have a clear symmetry problem and neglect the inherent objective hierarchy built into these objective spaces. We introduce Priority-Constrained Descent (PCD), a gradient-based optimization framework designed to explicitly exploit hierarchical objective structures. PCD preserves the direction of primary descent whilst allowing for the minimal distortion necessary to guarantee progress on secondary objectives, controlled by a single $τ\in [0, 1]$ that dictates the strength of the distortion. The resulting formulation is invariant to objective scaling and admits exact closed-form solutions for problems with two and three objectives. We evaluate PCD within structured network compression settings, unstructured sparsity and low-rankness, and across a variety of synthetic experiments, showing Pareto dominance and better per-objective performance with secondary progress guarantees over existing methods, further exhibiting the interpretable trade-off that $τ$ provides.

Related papers

• Towards Pareto-Optimal Tool-Integrated Agents with Pareto Ranking Policy Optimization [54.855135506924775]
  We introduce a two-stage multi-objective optimization framework for aligning tool-using large language models (LLMs) under competing objectives.<n>This design enables fine-grained, action-level optimization across multiple conflicting objectives.
  arXiv  Detail & Related papers  (2026-06-15T01:58:07Z)
• Rethinking Layer Redundancy in Large Language Models: Calibration Objectives and Search for Depth Pruning [4.422051502416615]
  We show that different objectives yield qualitatively different redundant layers, and that perplexity and downstream accuracy rankings do not consistently align.<n>Under a fixed objective, however, search algorithms tend to produce similar solutions.
  arXiv  Detail & Related papers  (2026-04-27T19:25:28Z)
• Reward-free Alignment for Conflicting Objectives [12.275610380458119]
  We propose a Reward-free Alignment framework for Conflicted Objectives (RACO)<n>RACO directly leverages pairwise preference data and resolves gradient conflicts via a novel clipped variant of conflict-averse gradient descent.<n>We provide convergence guarantees to Pareto-critical points that respect user-specified objective weights, and further show that clipping can strictly improve convergence rate in the two-objective setting.
  arXiv  Detail & Related papers  (2026-02-02T18:59:52Z)
• Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time [52.230936493691985]
  We propose SITAlign, an inference framework that addresses the multifaceted nature of alignment by maximizing a primary objective while satisfying threshold-based constraints on secondary criteria.<n>We provide theoretical insights by deriving sub-optimality bounds of our satisficing based inference alignment approach.
  arXiv  Detail & Related papers  (2025-05-29T17:56:05Z)
• Multi-start Optimization Method via Scalarization based on Target Point-based Tchebycheff Distance for Multi-objective Optimization [2.9248680865344348]
  Multi-objective optimization is crucial in scientific and industrial applications where solutions must balance trade-offs among conflicting objectives.<n>State-of-the-art methods, such as NSGA-III and MOEA/D, can handle many objectives but struggle with coverage issues.<n>We propose a novel multi-start optimization method that addresses these challenges.
  arXiv  Detail & Related papers  (2025-05-01T02:27:25Z)
• Goal-Conditioned Supervised Learning for Multi-Objective Recommendation [8.593384839118658]
  Multi-objective learning endeavors to concurrently optimize multiple objectives using a single model.<n>This paper introduces a Multi-Objective Goal-Conditioned Supervised Learning framework for automatically learning to achieve multiple objectives from offline sequential data.
  arXiv  Detail & Related papers  (2024-12-12T03:47:40Z)
• Deep Pareto Reinforcement Learning for Multi-Objective Recommender Systems [54.2484458418885]
  optimizing multiple objectives simultaneously is an important task for recommendation platforms.<n>Existing multi-objective recommender systems do not systematically consider such dynamic relationships.
  arXiv  Detail & Related papers  (2024-07-04T02:19:49Z)
• Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment [103.12563033438715]
  Alignment in artificial intelligence pursues consistency between model responses and human preferences as well as values. Existing alignment techniques are mostly unidirectional, leading to suboptimal trade-offs and poor flexibility over various objectives. We introduce controllable preference optimization (CPO), which explicitly specifies preference scores for different objectives.
  arXiv  Detail & Related papers  (2024-02-29T12:12:30Z)
• Cycle Consistency Driven Object Discovery [75.60399804639403]
  We introduce a method that explicitly optimize the constraint that each object in a scene should be associated with a distinct slot. By integrating these consistency objectives into various existing slot-based object-centric methods, we showcase substantial improvements in object-discovery performance. Our results suggest that the proposed approach not only improves object discovery, but also provides richer features for downstream tasks.
  arXiv  Detail & Related papers  (2023-06-03T21:49:06Z)
• Alleviating Search Bias in Bayesian Evolutionary Optimization with Many Heterogeneous Objectives [9.139734850798124]
  We deal with multi-objective optimization problems with heterogeneous objectives (HE-MOPs) A new acquisition function that mitigates search bias towards the fast objectives is suggested. We demonstrate the effectiveness of the proposed algorithm by testing it on widely used multi-/many-objective benchmark problems.
  arXiv  Detail & Related papers  (2022-08-25T17:07:40Z)
• Generative multitask learning mitigates target-causing confounding [61.21582323566118]
  We propose a simple and scalable approach to causal representation learning for multitask learning. The improvement comes from mitigating unobserved confounders that cause the targets, but not the input. Our results on the Attributes of People and Taskonomy datasets reflect the conceptual improvement in robustness to prior probability shift.
  arXiv  Detail & Related papers  (2022-02-08T20:42:14Z)

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.