mlsanityData to 7 Oct 2026

Holistic Deep Learning

arXiv 2110.15829 ↗First posted 29 Oct 2021cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 42 of its 66 references that are in the map. First posted on arXiv 29 Oct 2021.

Builds on

42 of 66 references.

References · 42

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  8. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  9. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  10. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  11. 2016Pruning Filters for Efficient ConvNetscited by 1,129
  12. 2017Learning Sparse Neural Networks through L0 Regularizationcited by 571
30 more
  1. 2021Just Train Twice: Improving Group Robustness without Training Group Informationcited by 522
  2. 2021Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networkscited by 521
  3. 2019The State of Sparsity in Deep Neural Networkscited by 471
  4. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  5. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 439
  6. 2017Mitigating Adversarial Effects Through Randomizationcited by 382
  7. 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 254
  8. 2017Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradientscited by 236
  9. 2020The Computational Limits of Deep Learningcited by 188
  10. 2019Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterizationcited by 187
  11. 2017Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulationcited by 182
  12. 2018Semidefinite relaxations for certifying robustness to adversarial examplescited by 178
  13. 2018Discrimination-aware Channel Pruning for Deep Neural Networkscited by 171
  14. 2017Deep Rewiring: Training very sparse deep networkscited by 136
  15. 2018A Dual Approach to Scalable Verification of Deep Networkscited by 125
  16. 2018Strong mixed-integer programming formulations for trained neural networkscited by 115
  17. 2019Winning the Lottery with Continuous Sparsificationcited by 99
  18. 2017Exploring Sparsity in Recurrent Neural Networkscited by 75
  19. 2019Distributionally Robust Optimization and Generalization in Kernel Methodscited by 73
  20. 2018Deflecting Adversarial Attacks with Pixel Deflectioncited by 71
  21. 2018How Complex is your classification problem? A survey on measuring classification complexitycited by 66
  22. 2020Beyond Perturbations: Learning Guarantees with Arbitrary Adversarial Test Examplescited by 44
  23. 2018Deep Defense: Training DNNs with Improved Adversarial Robustnesscited by 41
  24. 2017The Robust Manifold Defense: Adversarial Training using Generative Modelscited by 35
  25. 2019Sparse Regression: Scalable algorithms and empirical performancecited by 27
  26. 2020Optimal Policy Treescited by 19
  27. 2018Fast Convex Pruning of Deep Neural Networkscited by 8
  28. 2020Deflecting Adversarial Attackscited by 7
  29. 2018VectorDefense: Vectorization as a Defense to Adversarial Examplescited by 6
  30. 2018Fortified Networks: Improving the Robustness of Deep Networks by Modeling the Manifold of Hidden Representationscited by 4

Built on by

Not cited yet.