The optimization of over-parameterized deep neural networks represents a large-scale, high-dimensional, and strongly non-convex decision problem that challenges existing optimization frameworks. Current evolutionary and gradient-based pruning methods often struggle to scale to such dimensionalities, as they rely on flat search spaces, scalarized objectives, or repeated retraining, leading to premature convergence and prohibitive computational cost. This paper introduces a hierarchical importance-guided evolutionary framework that reformulates convolutional network pruning as a tractable large-scale multi-objective optimization problem. In the first phase, a continuous evolutionary search performs coarse exploration of weight-wise pruning thresholds to shrink the search space and identify promising regions of the Pareto set. The second phase applies a fine-grained binary evolutionary optimization constrained to the surviving weights, where importance-aware sampling and adaptive variation operators refine local search in the sparse region of the Pareto set. This hierarchical design combines global exploration and localized exploitation to achieve a well-distributed Pareto set of networks balancing compactness and accuracy. Empirical results on CIFAR-10 and CIFAR-100 using ResNet-56 and ResNet-110 confirm the method's effectiveness compared to existing evolutionary approaches: pruning achieves up to 51.9\% and 38.9\% parameter reductions with almost no accuracy loss compared to state-of-the-art evolutionary DNN pruning methods. The proposed method contributes a scalable evolutionary approach for solving very-large-scale multi-objective optimization problems, offering a general paradigm extendable to other domains where the decision space is exponentially large, objective functions are conflicting, and efficient trade-off discovery is essential.

翻译：过参数化深度神经网络的优化是一个大规模、高维、强非凸的决策问题，对现有优化框架构成挑战。当前的进化方法和基于梯度的剪枝方法通常难以扩展到此类维度，因为它们依赖于平坦搜索空间、标量化目标或重复训练，导致早熟收敛和过高的计算成本。本文提出一种层次化重要性引导的进化框架，将卷积网络剪枝重新表述为可处理的大规模多目标优化问题。第一阶段，连续进化搜索对权重级剪枝阈值进行粗粒度探索，以缩减搜索空间并识别帕累托集中的有前景区域。第二阶段在剩余权重上应用细粒度二元进化优化，其中重要性感知采样和自适应变异算子优化帕累托集稀疏区域中的局部搜索。这种层次化设计结合全局探索与局部开发，可获得平衡紧凑性与准确性的分布良好的帕累托网络集。在CIFAR-10和CIFAR-100数据集上使用ResNet-56和ResNet-110的实验结果验证了该方法相较于现有进化方法的有效性：与最先进的进化DNN剪枝方法相比，本方法在几乎不损失准确率的情况下实现了高达51.9%和38.9%的参数缩减。所提方法为求解超大规模多目标优化问题提供了一种可扩展的进化途径，其通用范式可扩展至其他决策空间呈指数级增长、目标函数相互冲突且需要高效折衷探索的领域。