Built on

Belkin, M., Hsu, D., and Xu, J. (2019), “Two models of double descent for weak features,” arXiv preprint arXiv:1903.07571
Original
1903
Earlier work this paper cites.
Hastie, T., Montanari, A., Rosset, S., and Tibshirani, R. J. (2019), “Surprises in high-dimensional ridgeless least squares interpolation,” arXiv preprint arXiv:1903.08560
Original
1903
Earlier work this paper cites.
Raghunathan, A., Xie, S. M., Yang, F., Duchi, J. C., and Liang, P. (2019), “Adversarial training can hurt generalization,” arXiv preprint arXiv:1906.06032
Original
1906
Earlier work this paper cites.
Zhai, R., Cai, T., He, D., Dan, C., He, K., Hopcroft, J., and Wang, L. (2019), “Adversarially robust generalization just requires more unlabeled data,” arXiv preprint arXiv:1906.00555
Original
1906
Earlier work this paper cites.
Wong, E., Rice, L., and Kolter, J. Z. (2020), “Fast is better than free: Revisiting adversarial training,” arXiv preprint arXiv:2001.03994
Original
2001
Earlier work this paper cites.
Chen, L., Min, Y., Zhang, M., and Karbasi, A. (2020), “More data can expand the generalization gap between adversarially robust and standard models,” arXiv preprint arXiv:2002.04725
Original
2002
Earlier work this paper cites.
Javanmard, A., Soltanolkotabi, M., and Hassani, H. (2020), “Precise tradeoffs in adversarial training for linear regression,” arXiv preprint arXiv:2002.10477
Original
2002
Earlier work this paper cites.
Min, Y., Chen, L., and Karbasi, A. (2020), “The curious case of adversarially robust models: More data can help, double descend, or hurt generalization,” arXiv preprint arXiv:2002.11080
Original
2002
Earlier work this paper cites.
Rice, L., Wong, E., and Kolter, J. Z. (2020), “Overfitting in adversarially robust deep learning,” arXiv preprint arXiv:2002.11569
Original
2002
Earlier work this paper cites.
Zhang, Y., Plevrakis, O., Du, S. S., Li, X., Song, Z., and Arora, S. (2020), “Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality,” arXiv preprint arXiv:2002.06668
Original
2002
Earlier work this paper cites.
Li, B., Wang, S., Jia, Y., Lu, Y., Zhong, Z., Carin, L., and Jana, S. (2020), “Towards Practical Lottery Ticket Hypothesis for Adversarial Training,” arXiv preprint arXiv:2003.05733
Original
2003
Earlier work this paper cites.
Wu, D., Wang, Y., and Xia, S.-t. (2020), “Revisiting Loss Landscape for Adversarial Robustness,” arXiv preprint arXiv:2004.05884
Original
2004
Earlier work this paper cites.
Allen-Zhu, Z. and Li, Y. (2020), “Feature Purification: How Adversarial Training Performs Robust Deep Learning,” arXiv preprint arXiv:2005.10190
Original
2005
Earlier work this paper cites.
Lee, K. and Chandrakasan, A. P. (2020), “Rethinking Empirical Evaluation of Adversarial Robustness Using First-Order Attack Methods,” arXiv preprint arXiv:2006.01304
Original
2006
Earlier work this paper cites.
Xie, C., Tan, M., Gong, B., Yuille, A., and Le, Q. V. (2020), “Smooth adversarial training,” arXiv preprint arXiv:2006.14536
Original
2006
Earlier work this paper cites.

Similar

Bai, Z.-D. and Yin, Y.-Q. (2008), “Limit of the smallest eigenvalue of a large dimensional sample covariance matrix,” in Advances In Statistics
2008
Cited alongside, same era.
Bickel, P. J., Ritov, Y., and Tsybakov, A. B. (2009), “Simultaneous analysis of Lasso and Dantzig selector,” The Annals of Statistics
2009
Cited alongside, same era.
Ing, C.-K. and Lai, T. L. (2011), “A stepwise regression method and consistent model selection for high-dimensional sparse linear models,” Statistica Sinica
2011
Cited alongside, same era.
Belloni, A. and Chernozhukov, V. (2013), “Least squares after model selection in high-dimensional sparse models,” Bernoulli
2013
Cited alongside, same era.
Biggio, B., Corona, I., Maiorca, D., Nelson, B., Šrndić, N., Laskov, P., Giacinto, G., and Roli, F. (2013), “Evasion attacks against machine learning at test time,” in Joint European Conference on Machine Learning and Knowledge Discovery in Databases

Then

Sinha, A., Namkoong, H., and Duchi, J. C. (2018), “Certifiable distributional robustness with principled adversarial training,” in 6th International Conference on Learning Representations
2018
Later among the works it cites.
Tao, G., Ma, S., Liu, Y., and Zhang, X. (2018), “Attacks meet interpretability: Attribute-steered detection of adversarial samples,” in Advances in Neural Information Processing Systems
2018
Later among the works it cites.
Arora, S., Du, S. S., Hu, W., Li, Z., and Wang, R. (2019), “Fine-grained analysis of optimization and generalization for overparameterized two-layer neural networks,” in Proceedings of the 36th International Conference on Machine Learning
2019
Later among the works it cites.
Du, S. S., Lee, J. D., Li, H., Wang, L., and Zhai, X. (2019), “Gradient descent finds global minima of deep neural networks,” in Proceedings of the 36th International Conference on Machine Learning
2019
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…

2020

On the Generalization Properties of Adversarial Training

Xing, Yue, Song, Qifan, Cheng, Guang

Understand

Modern machine learning and deep learning models are shown to be vulnerable when testing data are slightly perturbed.

Existing theoretical studies of adversarial training algorithms mostly focus on either adversarial training losses or local convergence properties.
In contrast, this paper studies the generalization performance of a generic adversarial training algorithm.
Specifically, we consider linear regression models and two-layer neural networks (with lazy training) using squared loss under low-dimensional and high-dimensional regimes.

Built on

Belkin, M., Hsu, D., and Xu, J. (2019), “Two models of double descent for weak features,” arXiv preprint arXiv:1903.07571
Original
1903
Earlier work this paper cites.
Hastie, T., Montanari, A., Rosset, S., and Tibshirani, R. J. (2019), “Surprises in high-dimensional ridgeless least squares interpolation,” arXiv preprint arXiv:1903.08560
Original
1903
Earlier work this paper cites.
Raghunathan, A., Xie, S. M., Yang, F., Duchi, J. C., and Liang, P. (2019), “Adversarial training can hurt generalization,” arXiv preprint arXiv:1906.06032
Original
1906
Earlier work this paper cites.
Zhai, R., Cai, T., He, D., Dan, C., He, K., Hopcroft, J., and Wang, L. (2019), “Adversarially robust generalization just requires more unlabeled data,” arXiv preprint arXiv:1906.00555
Original
1906
Earlier work this paper cites.
Wong, E., Rice, L., and Kolter, J. Z. (2020), “Fast is better than free: Revisiting adversarial training,” arXiv preprint arXiv:2001.03994
Original
2001
Earlier work this paper cites.
Chen, L., Min, Y., Zhang, M., and Karbasi, A. (2020), “More data can expand the generalization gap between adversarially robust and standard models,” arXiv preprint arXiv:2002.04725
Original
2002
Earlier work this paper cites.
Javanmard, A., Soltanolkotabi, M., and Hassani, H. (2020), “Precise tradeoffs in adversarial training for linear regression,” arXiv preprint arXiv:2002.10477
Original
2002
Earlier work this paper cites.
Min, Y., Chen, L., and Karbasi, A. (2020), “The curious case of adversarially robust models: More data can help, double descend, or hurt generalization,” arXiv preprint arXiv:2002.11080
Original
2002
Earlier work this paper cites.
Rice, L., Wong, E., and Kolter, J. Z. (2020), “Overfitting in adversarially robust deep learning,” arXiv preprint arXiv:2002.11569
Original
2002
Earlier work this paper cites.
Zhang, Y., Plevrakis, O., Du, S. S., Li, X., Song, Z., and Arora, S. (2020), “Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality,” arXiv preprint arXiv:2002.06668
Original
2002
Earlier work this paper cites.
Li, B., Wang, S., Jia, Y., Lu, Y., Zhong, Z., Carin, L., and Jana, S. (2020), “Towards Practical Lottery Ticket Hypothesis for Adversarial Training,” arXiv preprint arXiv:2003.05733
Original
2003
Earlier work this paper cites.
Wu, D., Wang, Y., and Xia, S.-t. (2020), “Revisiting Loss Landscape for Adversarial Robustness,” arXiv preprint arXiv:2004.05884
Original
2004
Earlier work this paper cites.
Allen-Zhu, Z. and Li, Y. (2020), “Feature Purification: How Adversarial Training Performs Robust Deep Learning,” arXiv preprint arXiv:2005.10190
Original
2005
Earlier work this paper cites.
Lee, K. and Chandrakasan, A. P. (2020), “Rethinking Empirical Evaluation of Adversarial Robustness Using First-Order Attack Methods,” arXiv preprint arXiv:2006.01304
Original
2006
Earlier work this paper cites.
Xie, C., Tan, M., Gong, B., Yuille, A., and Le, Q. V. (2020), “Smooth adversarial training,” arXiv preprint arXiv:2006.14536
Original
2006
Earlier work this paper cites.

Similar

Bai, Z.-D. and Yin, Y.-Q. (2008), “Limit of the smallest eigenvalue of a large dimensional sample covariance matrix,” in Advances In Statistics
2008
Cited alongside, same era.
Bickel, P. J., Ritov, Y., and Tsybakov, A. B. (2009), “Simultaneous analysis of Lasso and Dantzig selector,” The Annals of Statistics
2009
Cited alongside, same era.
Ing, C.-K. and Lai, T. L. (2011), “A stepwise regression method and consistent model selection for high-dimensional sparse linear models,” Statistica Sinica
2011
Cited alongside, same era.
Belloni, A. and Chernozhukov, V. (2013), “Least squares after model selection in high-dimensional sparse models,” Bernoulli
2013
Cited alongside, same era.
Biggio, B., Corona, I., Maiorca, D., Nelson, B., Šrndić, N., Laskov, P., Giacinto, G., and Roli, F. (2013), “Evasion attacks against machine learning at test time,” in Joint European Conference on Machine Learning and Knowledge Discovery in Databases

Then

Sinha, A., Namkoong, H., and Duchi, J. C. (2018), “Certifiable distributional robustness with principled adversarial training,” in 6th International Conference on Learning Representations
2018
Later among the works it cites.
Tao, G., Ma, S., Liu, Y., and Zhang, X. (2018), “Attacks meet interpretability: Attribute-steered detection of adversarial samples,” in Advances in Neural Information Processing Systems
2018
Later among the works it cites.
Arora, S., Du, S. S., Hu, W., Li, Z., and Wang, R. (2019), “Fine-grained analysis of optimization and generalization for overparameterized two-layer neural networks,” in Proceedings of the 36th International Conference on Machine Learning
2019
Later among the works it cites.
Du, S. S., Lee, J. D., Li, H., Wang, L., and Zhai, X. (2019), “Gradient descent finds global minima of deep neural networks,” in Proceedings of the 36th International Conference on Machine Learning
2019
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

2013

Cited alongside, same era.

Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I. J., and Fergus, R. (2014), “Intriguing properties of neural networks,” in 2nd International Conference on Learning Representations

2014

Cited alongside, same era.

Shaham, U., Yamada, Y., and Negahban, S. (2015), “Understanding adversarial training: Increasing local stability of neural nets through robust optimization,” arXiv preprint arXiv:1511.05432

Original

2015

Cited alongside, same era.

Moosavi-Dezfooli, S.-M., Fawzi, A., and Frossard, P. (2016), “Deepfool: a simple and accurate method to fool deep neural networks,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition

2016

Cited alongside, same era.

Papernot, N., McDaniel, P., Swami, A., and Harang, R. (2016a), “Crafting adversarial input sequences for recurrent neural networks,” in Military Communications Conference, MILCOM 2016-2016 IEEE

2016

Cited alongside, same era.

Papernot, N., McDaniel, P. D., Jha, S., Fredrikson, M., Celik, Z. B., and Swami, A. (2016b), “The limitations of deep learning in adversarial settings,” in IEEE European Symposium on Security and Privacy, EuroS&P 2016, Saarbrücken, Germany, March 21-24, 2016

2016

Cited alongside, same era.

Jalal, A., Ilyas, A., Daskalakis, C., and Dimakis, A. G. (2017), “The robust manifold defense: Adversarial training using generative models,”

2017

Cited alongside, same era.

Du, S. S., Zhai, X., Poczos, B., and Singh, A. (2018), “Gradient descent provably optimizes over-parameterized neural networks,” arXiv preprint arXiv:1810.02054

Original

2018

Cited alongside, same era.

Gao, R., Cai, T., Li, H., Hsieh, C., Wang, L., and Lee, J. D. (2019), “Convergence of adversarial training in overparametrized neural networks,” in Advances in Neural Information Processing Systems

2019