A tunable loss function for binary classification T Sypherd, M Diaz, L Sankar, P Kairouz 2019 IEEE international symposium on information theory (ISIT), 2479-2483, 2019 | 35 | 2019 |
A tunable loss function for robust classification: Calibration, landscape, and generalization T Sypherd, M Diaz, JK Cava, G Dasarathy, P Kairouz, L Sankar IEEE Transactions on Information Theory 68 (9), 6021-6051, 2022 | 25 | 2022 |
Realizing GANs via a tunable loss function GR Kurri, T Sypherd, L Sankar 2021 IEEE Information Theory Workshop (ITW), 1-6, 2021 | 16 | 2021 |
α-GAN: Convergence and estimation guarantees GR Kurri, M Welfert, T Sypherd, L Sankar 2022 IEEE International Symposium on Information Theory (ISIT), 276-281, 2022 | 10 | 2022 |
Being properly improper T Sypherd, R Nock, L Sankar arXiv preprint arXiv:2106.09920, 2021 | 8* | 2021 |
On the α-loss landscape in the logistic model T Sypherd, M Diaz, L Sankar, G Dasarathy 2020 IEEE International Symposium on Information Theory (ISIT), 2700-2705, 2020 | 7 | 2020 |
Smoothly giving up: Robustness for simple models T Sypherd, N Stromberg Proceedings of The 26th International Conference on Artificial Intelligence …, 2023 | 2 | 2023 |
A tunable loss function for classification T Sypherd, M Diaz, H Laddha, L Sankar, P Kairouz, G Dasarathy CoRR, abs/1906.02314, 2019 | 2 | 2019 |
AugLoss: A Learning Methodology for Real-World Dataset Corruption K Otstot, JK Cava, T Sypherd, L Sankar arXiv preprint arXiv:2206.02286, 2022 | | 2022 |
A Tunable Loss Function for Robust, Rigorous, and Reliable Machine Learning T Sypherd Arizona State University, 2022 | | 2022 |