|
2026 Conference Publication Is the last layer sufficient for uncertainty quantification?Wilson, Joseph, van der Heide, Chris, Hodgkinson, Liam and Roosta, Fred (2026). Is the last layer sufficient for uncertainty quantification?. The Forty-Third International Conference on Machine Learning (ICML 2026), Seoul, South Korea, July 6–11, 2026. Newton Highlands, MA, United States: Open Review. |
|
2026 Conference Publication Counterfactual explanations on robust perceptual geodesicsZaher, Eslam, Trzaskowski, Maciej, Nguyen, Quan and Roosta, Fred (2026). Counterfactual explanations on robust perceptual geodesics. International Conference on Learning Representations (ICLR), Rio de Janeiro, Brazil, 23 - 25 April 2026. |
|
2025 Conference Publication Determinant estimation under memory constraints and neural scaling lawsAmeli, Siavash, van der Heide, Chris, Hodgkinson, Liam, Roosta, Fred and Mahoney, Michael W. (2025). Determinant estimation under memory constraints and neural scaling laws. International Conference on Machine Learning, Vancouver, BC, Canada, 13-19 July 2025. San Diego, CA USA: Proceedings of Machine Learning Research. doi: 10.1007/BF02066732 |
|
2025 Conference Publication Importance sampling for nonlinear modelsRajmohan, Prakash Palanivelu and Roosta, Fred (2025). Importance sampling for nonlinear models. International Conference on Machine Learning, Vancouver, BC, Canada, 13-19 July 2025. San Diego, CA USA: Proceedings of Machine Learning Research. |
|
2025 Conference Publication Training-free medical image inverses via bi-level guided diffusion modelsAskari, Hossein, Roosta, Fred and Sun, Hongfu (2025). Training-free medical image inverses via bi-level guided diffusion models. 2025 Winter Conference on Applications of Computer Vision-WACV, Tucson, AZ, United States, 28 February-4 March 2025. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/wacv61041.2025.00018 |
|
2025 Conference Publication Uncertainty quantification with the empirical neural tangent kernelWilson, Joseph, van der Heide, Chris, Hodgkinson, Liam and Roosta, Fred (2025). Uncertainty quantification with the empirical neural tangent kernel. NIPS '25: 39th International Conference on Neural Information Processing Systems, San Diego, CA, United States, 2-7 December 2025. Maryland Heights, MO, United States: Morgan Kaufmann Publishers. doi: 10.52202/085713-4983 |
|
2025 Conference Publication Importance sampling for nonlinear modelsRajmohan, Prakash P. and Roosta, Fred (2025). Importance sampling for nonlinear models. International Conference on Machine Learning, Vancouver, BC, Canada, 13 - 19 July 2025. Cambridge, MA, United States: ML Research Press. |
|
2025 Conference Publication Latent Refinement via Flow Matching for Training-free Linear Inverse Problem SolvingAskari, Hossein, Luo, Yadan, Sun, Hongfu and Roosta, Fred (2025). Latent Refinement via Flow Matching for Training-free Linear Inverse Problem Solving. 39th Conference on Neural Information Processing Systems (NeurIPS 2025), San Diego, CA United States, 2-7 December 2025. San Diego, CA United States: Neural Information Processing Systems Foundation. doi: 10.52202/085713-3606 |
|
2025 Conference Publication Importance sampling for nonlinear modelsRajmohan, Prakash P. and Roosta, Fred (2025). Importance sampling for nonlinear models. 42nd International Conference on Machine Learning ICML Annual, Vancouver, BC, Canada, 13 - 19 July 2025. San Diego, CA, United States: Journal Machine Learning Research. |
|
2024 Conference Publication Inexact Newton-type methods for optimisation with nonnegativity constraintsSmee, Oscar and Roosta, Fred (2024). Inexact Newton-type methods for optimisation with nonnegativity constraints. International Conference on Machine Learning, Vienna, Austria, 21-27 July 2024. Proceedings of Machine Learning Research. |
|
2024 Conference Publication Manifold integrated gradients: Riemannian geometry for feature attributionZaher, Eslam, Trzaskowski, Maciej, Nguyen, Quan and Roosta, Fred (2024). Manifold integrated gradients: Riemannian geometry for feature attribution. International Conference on Machine Learning, Vienna, Austria, 21-27 July 2024. Proceedings of Machine Learning Research. |
|
2023 Conference Publication Monotonicity and double descent in uncertainty estimation with gaussian processesHodgkinson, Liam, Van Der Heide, Chris, Roosta, Fred and Mahoney, Michael W. (2023). Monotonicity and double descent in uncertainty estimation with gaussian processes. International Conference on Machine Learning, Honolulu, HI United States, 23 - 29 July 2023. San Diego, CA United States: International Conference on Machine Learning. |
|
2022 Conference Publication Crop type prediction utilising a long short-term memory with a self-attention for winter crops in AustraliaNguyen, Dung, Zhao, Yan, Zhang, Yifan, Huynh, Anh Ngoc-Lan, Roosta, Fred, Hammer, Graeme, Chapman, Scott and Potgieter, Andries (2022). Crop type prediction utilising a long short-term memory with a self-attention for winter crops in Australia. IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium, Kuala Lumpur, Malaysia, 17-22 July 2022. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/IGARSS46834.2022.9883737 |
|
2021 Conference Publication Shadow Manifold Hamiltonian Monte Carlovan der Heide, Chris, Hodgkinson, Liam, Roosta, Fred and Kroese, Dirk (2021). Shadow Manifold Hamiltonian Monte Carlo. International Conference on Artificial Intelligence and Statistics, Online, 27-30- July 2021. Tempe, AZ United States: ML Research Press. |
|
2021 Conference Publication Avoiding kernel fixed points: Computing with ELU and GELU infinite networksTsuchida, Russell, Pearce, Tim, van der Heide, Chris, Roosta, Fred and Gallagher, Marcus (2021). Avoiding kernel fixed points: Computing with ELU and GELU infinite networks. 35th AAAI Conference on Artificial Intelligence, AAAI 2021, Online, 2 - 9 February 2021. Menlo Park, CA United States: Association for the Advancement of Artificial Intelligence. doi: 10.1609/aaai.v35i11.17197 |
|
2021 Conference Publication Non-PSD matrix sketching with applications to regression and optimizationFeng, Zhili, Roosta, Fred and Woodruff, David P. (2021). Non-PSD matrix sketching with applications to regression and optimization. Conference on Uncertainty in Artificial Intelligence, Online, 27-29 July 2021. San Diego, CA United States: Association For Uncertainty in Artificial Intelligence (AUAI). |
|
2021 Conference Publication Stochastic continuous normalizing flows: training SDEs as ODEsHodgkinson, Liam, van der Heide, Chris, Roosta, Fred and Mahoney, Michael W. (2021). Stochastic continuous normalizing flows: training SDEs as ODEs. Conference on Uncertainty in Artificial Intelligence, Online, 27-29 July 2021. San Diego, CA, United States: Association For Uncertainty in Artificial Intelligence (AUAI). |
|
2021 Conference Publication Avoiding kernel fixed points: computing with ELU and GELU infinite networksTsuchida, Russell, Pearce, Tim, van der Heide, Chris, Roosta, Fred and Gallagher, Marcus (2021). Avoiding kernel fixed points: computing with ELU and GELU infinite networks. 35th AAAI Conference on Artificial Intelligence / 33rd Conference on Innovative Applications of Artificial Intelligence / 11th Symposium on Educational Advances in Artificial Intelligence, Electr Network, 2-9 February 2021. Washington, DC, United States: Association for the Advancement of Artificial Intelligence. |
|
2020 Conference Publication Newton-admm: a distributed GPU-accelerated optimizer for multiclass classification problemsFang, Chih-Hao, Kylasa, Sudhir B., Roosta, Fred, Mahoney, Michael W. and Grama, Ananth (2020). Newton-admm: a distributed GPU-accelerated optimizer for multiclass classification problems. International Conference on High Performance Computing, Networking, Storage and Analysis (SC), Atlanta, GA, United States, 9-19 November 2020. Piscataway, NJ, United States: IEEE Computer Society. doi: 10.1109/SC41405.2020.00061 |
|
2020 Conference Publication DINO: Distributed Newton-type optimization methodCrane, Rixon and Roosta, Fred (2020). DINO: Distributed Newton-type optimization method. International Conference on Machine Learning, Online, 12-18 July 2020. San Diego, CA United States: International Conference on Machine Learning. |
