Skip to main content
Back to KTH start page

Publications by Erik Englesson

Peer reviewed

Articles

[1]
M. Gamba et al., "Deep Double Descent via Smooth Interpolation," Transactions on Machine Learning Research, vol. 2023, no. 4, 2023.
[2]
E. Englesson, A. Mehrpanah and H. Azizpour, "Logistic-Normal Likelihoods for Heteroscedastic Label Noise," Transactions on Machine Learning Research, vol. 2023, no. 8, 2023.

Conference papers

[3]
A. Mehrpanah, E. Englesson and H. Azizpour, "On Spectral Properties of Gradient-Based Explanation Methods," in Computer Vision – ECCV 2024 - 18th European Conference, Proceedings, 2025, pp. 282-299.
[4]
A. Nilsson et al., "Indirectly Parameterized Concrete Autoencoders," in International Conference on Machine Learning, ICML 2024, 2024, pp. 38237-38252.
[5]
E. Englesson and H. Azizpour, "Robust Classification via Regression for Learning with Noisy Labels," in Proceedings ICLR 2024 - The Twelfth International Conference on Learning Representations, 2024.
[6]
E. Englesson and H. Azizpour, "Consistency Regularization Can Improve Robustness to Label Noise," in International Conference on Machine Learning (ICML) Workshops, 2021 Workshop on Uncertainty and Robustness in Deep Learning, 2021.
[7]
E. Englesson and H. Azizpour, "Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels," in Proceedings 35th Conference on Neural Information Processing Systems (NeurIPS 2021)., 2021.
[8]
E. Englesson and H. Azizpour, "Efficient Evaluation-Time Uncertainty Estimation by Improved Distillation," in International Conference on Machine Learning (ICML) Workshops, 2019 Workshop on Uncertainty and Robustness in Deep Learning, 2019.

Non-peer reviewed

Theses

[9]
E. Englesson, "On Label Noise in Image Classification : An Aleatoric Uncertainty Perspective," Doctoral thesis Stockholm : KTH Royal Institute of Technology, TRITA-EECS-AVL, 2024:45, 2024.
Latest sync with DiVA:
2025-07-16 22:27:30 UTC