Not All Objectives Are Born Equal: Priority-Constrained Descent for Hierarchical Multi-Objective Optimization
cs.LG, stat.ML
Submitted: 2026-06-28
Updated: 2026-09-21
Comments: 33 pages, 14 figures, 6 tables
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications
- Cooper: A Library for Constrained Optimization in Deep Learning
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Adam: A Method for Stochastic Optimization
- Exact Pareto Optimal Search for Multi-Task Learning and Multi-Criteria Decision-Making
- Learning the Pareto Front with Hypernetworks
- Empirical Analysis of the Hessian of Over-Parametrized Neural Networks
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks