The pursuit of optimal trade-offs in high-dimensional search spaces under stringent computational constraints poses a fundamental challenge for contemporary multi-objective optimization. We develop NeuroPareto, a cohesive architecture that integrates rank-centric filtering, uncertainty disentanglement, and history-conditioned acquisition strategies to navigate complex objective landscapes. A calibrated Bayesian classifier estimates epistemic uncertainty across non-domination tiers, enabling rapid generation of high-quality candidates with minimal evaluation cost. Deep Gaussian Process surrogates further separate predictive uncertainty into reducible and irreducible components, providing refined predictive means and risk-aware signals for downstream selection. A lightweight acquisition network, trained online from historical hypervolume improvements, guides expensive evaluations toward regions balancing convergence and diversity. With hierarchical screening and amortized surrogate updates, the method maintains accuracy while keeping computational overhead low. Experiments on DTLZ and ZDT suites and a subsurface energy extraction task show that NeuroPareto consistently outperforms classifier-enhanced and surrogate-assisted baselines in Pareto proximity and hypervolume.

翻译：在严格的计算约束下，于高维搜索空间中寻求最优权衡，是当代多目标优化面临的一项根本性挑战。我们提出了NeuroPareto，一种集成了基于排序的过滤、不确定性解耦和基于历史信息的获取策略的连贯架构，用以探索复杂的目标空间。一个经过校准的贝叶斯分类器估计跨非支配层级的知识不确定性，从而能够以最小的评估成本快速生成高质量候选解。深度高斯过程代理模型进一步将预测不确定性分解为可约和不可约分量，为下游选择提供精细化的预测均值及风险感知信号。一个轻量级的获取网络，通过在线学习历史超体积改进信息，引导代价高昂的评估过程趋向于平衡收敛性与多样性的区域。通过分层筛选和摊销式代理模型更新，该方法在保持精度的同时维持较低的计算开销。在DTLZ和ZDT测试集以及一项地下能源开采任务上的实验表明，NeuroPareto在帕累托逼近度和超体积指标上持续优于分类器增强型和代理模型辅助的基线方法。