This paper presents a novel holistic deep learning framework that simultaneously addresses the challenges of vulnerability to input perturbations, overparametrization, and performance instability from different train-validation splits. The proposed framework holistically improves accuracy, robustness, sparsity, and stability over standard deep learning models, as demonstrated by extensive experiments on both tabular and image data sets. The results are further validated by ablation experiments and SHAP value analysis, which reveal the interactions and trade-offs between the different evaluation metrics. To support practitioners applying our framework, we provide a prescriptive approach that offers recommendations for selecting an appropriate training loss function based on their specific objectives. All the code to reproduce the results can be found at https://github.com/kimvc7/HDL.

翻译：本文提出了一种新颖的整体深度学习框架，该框架同时应对了对输入扰动的脆弱性、过参数化以及不同训练验证分裂导致的性能不稳定性等挑战。通过在表格和图像数据集上的广泛实验表明，所提出的框架在准确性、鲁棒性、稀疏性和稳定性方面整体优于标准深度学习模型。消融实验和SHAP值分析进一步验证了结果，揭示了不同评估指标之间的相互作用与权衡。为支持应用我们框架的实践者，我们提供了一种规范性方法，根据其具体目标推荐选择合适的训练损失函数。重现结果的所有代码可在 https://github.com/kimvc7/HDL 获取。