Abstract
Machine learning models often suffer from a significant decline in performance when they encounter out-of-distribution (OOD) data that differs from the training distribution. The distribution shift can be broadly categorized into diversity shift and correlation shift. While seeking a flat minima in optimization has been shown to improve a neural network’s generalization performance with the assumption of independent and identical distribution (IID), it also has been shown to be an effective strategy for improving OOD generalization. However, previous studies potentially focused on addressing diversity shift, leaving the relationship between flat minima and correlation shift unresolved. To address the issue, we propose Sharpness-aware Invariant Risk Minimization (SIRM) as a novel approach to enhance generalization under correlation shift. Our method combines two parts: (1) Invariant risk minimization (IRM), which learns invariant relationships across multiple training environments, and (2) Sharpness-aware minimization (SAM), which finds a flat minima. Our analysis reveals that IRM does not guarantee flat minima and SAM does not improve the generalization in OOD. Moreover, we also analyze the relationship between flat minima and OOD data under correlation shift. Through extensive experiments conducted on image classification datasets, we demonstrate that our proposed method outperforms other methods with a competitive margin.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The meanings of environment, group, and domain are all referred to the hierarchy of a dataset, which can be seen as the same definition in this paper.
References
Arjovsky, M., Bottou, L., Gulrajani, I., Lopez-Paz, D.: Invariant risk minimization. arXiv preprint arXiv:1907.02893 (2019)
Bisla, D., Wang, J., Choromanska, A.: Low-pass filtering SGD for recovering flat optima in the deep learning optimization landscape. In: International Conference on Artificial Intelligence and Statistics, pp. 8299–8339. PMLR (2022)
Cha, J., et al.: SWAD: domain generalization by seeking flat minima. Adv. Neural. Inf. Process. Syst. 34, 22405–22418 (2021)
Chang, S., Zhang, Y., Yu, M., Jaakkola, T.: Invariant rationalization. In: International Conference on Machine Learning, pp. 1448–1458. PMLR (2020)
Chen, Y., et al.: Pareto invariant risk minimization: Towards mitigating the optimization dilemma in out-of-distribution generalization. In: The Eleventh International Conference on Learning Representations (2023)
Creager, E., Jacobsen, J.H., Zemel, R.: Environment inference for invariant learning. In: International Conference on Machine Learning, pp. 2189–2200. PMLR (2021)
Duchi, J.C., Namkoong, H.: Learning models with uniform performance via distributionally robust optimization. Ann. Stat. 49(3), 1378–1406 (2021)
Foret, P., Kleiner, A., Mobahi, H., Neyshabur, B.: Sharpness-aware minimization for efficiently improving generalization. In: International Conference on Learning Representations (2021)
Gulrajani, I., Lopez-Paz, D.: In search of lost domain generalization. In: International Conference on Learning Representations (2021)
He, H., Huang, G., Yuan, Y.: Asymmetric valleys: beyond sharp and flat local minima. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Hochreiter, S., Schmidhuber, J.: Flat minima. Neural Comput. 9(1), 1–42 (1997)
Hu, Z., Hong, L.J.: Kullback-leibler divergence constrained distributionally robust optimization. Available at Optimization Online 1(2), 1695–1724 (2013)
Huang, Z., et al.: Robust generalization against photon-limited corruptions via worst-case sharpness minimization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16175–16185 (2023)
Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D., Wilson, A.: Averaging weights leads to wider optima and better generalization. In: 34th Conference on Uncertainty in Artificial Intelligence 2018, UAI 2018, pp. 876–885 (2018)
Kaddour, J., Liu, L., Silva, R., Kusner, M.J.: When do flat minima optimizers work? Adv. Neural. Inf. Process. Syst. 35, 16577–16595 (2022)
Kamath, P., Tangella, A., Sutherland, D., Srebro, N.: Does invariant risk minimization capture invariance? In: International Conference on Artificial Intelligence and Statistics, pp. 4069–4077. PMLR (2021)
Keskar, N.S., Mudigere, D., Nocedal, J., Smelyanskiy, M., Tang, P.T.P.: On large-batch training for deep learning: Generalization gap and sharp minima. In: International Conference on Learning Representations (2017)
Kim, M., Li, D., Hu, S.X., Hospedales, T.: Fisher SAM: information geometry and sharpness aware minimisation. In: International Conference on Machine Learning, pp. 11148–11161. PMLR (2022)
Krueger, D., et al.: Out-of-distribution generalization via risk extrapolation (rex). In: International Conference on Machine Learning, pp. 5815–5826. PMLR (2021)
Lin, Y., Dong, H., Wang, H., Zhang, T.: Bayesian invariant risk minimization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16021–16030 (2022)
Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3730–3738 (2015)
McAllester, D.A.: Pac-bayesian model averaging. In: Proceedings of the Twelfth Annual Conference on Computational Learning Theory, pp. 164–170 (1999)
Petzka, H., Kamp, M., Adilova, L., Sminchisescu, C., Boley, M.: Relative flatness and generalization. In: In: Advances in Neural Information Processing Systems (2021)
Rame, A., Dancette, C., Cord, M.: Fishr: invariant gradient variances for out-of-distribution generalization. In: International Conference on Machine Learning, pp. 18347–18377. PMLR (2022)
Rame, A., Kirchmeyer, M., Rahier, T., Rakotomamonjy, A., patrick gallinari, Cord, M.: Diverse weight averaging for out-of-distribution generalization. In: Advances in Neural Information Processing Systems (2022)
Rangwani, H., Aithal, S.K., Mishra, M., Jain, A., Radhakrishnan, V.B.: A closer look at smoothness in domain adversarial training. In: International Conference on Machine Learning, pp. 18378–18399. PMLR (2022)
Rosenfeld, E., Ravikumar, P., Risteski, A.: The risks of invariant risk minimization. arXiv preprint arXiv:2010.05761 (2020)
Sagawa, S., Koh, P.W., Hashimoto, T.B., Liang, P.: Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization. In: International Conference on Learning Representations (ICLR) (2020)
Sagawa, S., Raghunathan, A., Koh, P.W., Liang, P.: An investigation of why overparameterization exacerbates spurious correlations. In: International Conference on Machine Learning, pp. 8346–8356. PMLR (2020)
Vapnik, V.: Statistical Learning Theory. Wiley, New York (1998)
Ye, N., et al.: OoD-bench: quantifying and understanding two dimensions of out-of-distribution generalization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7947–7958 (2022)
Yong, L., Zhu, S., Tan, L., Cui, P.: Zin: When and how to learn invariance without environment partition? In: Advances in Neural Information Processing Systems (2022)
Zhang, Y., Sharma, P., Ram, P., Hong, M., Varshney, K.R., Liu, S.: What is missing in IRM training and evaluation? challenges and solutions. In: The Eleventh International Conference on Learning Representations (2023)
Zhou, X., Lin, Y., Zhang, W., Zhang, T.: Sparse invariant risk minimization. In: International Conference on Machine Learning, pp. 27222–27244. PMLR (2022)
Acknowledgements
This work was supported by the Fundamental Research Funds for the Central Universities of China (2022JBMC009), the Natural Science Foundation of China (61972027), and the Beijing Municipal Natural Science Foundation (Grant No. 4212041).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Li, D., Teng, Z., Li, Q., Wang, Z. (2024). Sharpness-Aware Minimization for Out-of-Distribution Generalization. In: Luo, B., Cheng, L., Wu, ZG., Li, H., Li, C. (eds) Neural Information Processing. ICONIP 2023. Communications in Computer and Information Science, vol 1961. Springer, Singapore. https://doi.org/10.1007/978-981-99-8126-7_43
Download citation
DOI: https://doi.org/10.1007/978-981-99-8126-7_43
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8125-0
Online ISBN: 978-981-99-8126-7
eBook Packages: Computer ScienceComputer Science (R0)