Dr Fred Roosta-Khorasani

ARC DECRA Fellowship

School of Mathematics and Physics
Faculty of Science
fred.roosta@uq.edu.au
+61 7 336 53259

Overview

Research Interests

  • Machine Learning
  • Numerical Analysis
  • Numerical Optimization
  • Randomized Algorithms
  • Computational Statistics
  • Scientific Computing

Qualifications

  • Doctor of Philosophy, The University of British Columbia

Publications

  • Roosta-Khorasani, Farbod and Mahoney, Michael W. (2018) Sub-sampled Newton methods. Mathematical Programming, . doi:10.1007/s10107-018-1346-5

  • Cheng, Xiang, Roosta-Khorasani, Farbod, Palombo, Stefan, Bartlett, Peter L. and Mahoney, Michael W. (2018). FLAG n’ FLARE: fast linearly-coupled adaptive gradient methods. In: Amos Storkey and Fernando Perez-Cruz, Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics. Twenty-First International Conference on Artificial Intelligence and Statistics, Lanzarote, Canary Islands, (404-414). 9-11 April 2018.

  • Tsuchida, Russell, Roosta-Khorasani, Farbod and Gallagher, Marcus (2018). Invariance of weight distributions in rectified MLPs. In: Jennifer Dy and Andreas Krause, Proceedings of the 35th International Conference on Machine Learning. 35th International Conference on Machine Learning, Stockholm, Sweden, (4995-5004). 10-15 July 2018.

View all Publications

Grants

View all Grants

Supervision

  • Doctor Philosophy

  • Doctor Philosophy

  • (2018) Doctor Philosophy

View all Supervision

Publications

Book Chapter

  • Ye, Nan, Roosta-Khorasani, Farbod and Cui, Tiangang (2018). Optimization methods for inverse problems. In David R. Wood, Jan de Gier, Cheryl E. Praeger and Terence Tao (Ed.), 2017 MATRIX Annals (pp. 1-19) MATRIX Book Series: Springer.

Journal Article

Conference Publication

  • Cheng, Xiang, Roosta-Khorasani, Farbod, Palombo, Stefan, Bartlett, Peter L. and Mahoney, Michael W. (2018). FLAG n’ FLARE: fast linearly-coupled adaptive gradient methods. In: Amos Storkey and Fernando Perez-Cruz, Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics. Twenty-First International Conference on Artificial Intelligence and Statistics, Lanzarote, Canary Islands, (404-414). 9-11 April 2018.

  • Tsuchida, Russell, Roosta-Khorasani, Farbod and Gallagher, Marcus (2018). Invariance of weight distributions in rectified MLPs. In: Jennifer Dy and Andreas Krause, Proceedings of the 35th International Conference on Machine Learning. 35th International Conference on Machine Learning, Stockholm, Sweden, (4995-5004). 10-15 July 2018.

  • Levin, Keith, Roosta-Khorasani, Farbod , Mahoney, Michael W. and Priebe, Carey E. (2018). Out-of-sample extension of graph adjacency spectral embedding. In: Jennifer Dy and Andreas Krause, Proceedings of the 35th International Conference on Machine Learning. 35th International Conference on Machine Learning, Stockholm, Sweden, (2975-2984). 10-15 July 2018.

  • Wang, Shusen, Roosta-Khorasani, Farbod, Xu, Peng and Mahoney, Michael W. (2017). GIANT: Globally Improved Approximate Newton method for distributed optimization. In: Advances in Neural Information Processing Systems 31. Thirty-second Conference on Neural Information Processing Systems, Montreal Canada, (). 2-8 December 2018.

  • Bouchard, Kristofer E, Bujan, Alejandro F, Roosta-Khorasani, Farbod, Prabhat, Snijders, Jian-Hua Mao, Chang, Edward F, Mahoney, Michael W and Bhattacharyya, Sharmodeep (2017). The Union of Intersections (UoI) method for interpretable data driven discovery and prediction. In: 31st Annual Conference on Neural Information Processing Systems (NIPS), Long Beach, CA United States, (). 4-9 December 2017.

  • Shun, Julian, Roosta-Khorasani, Farbod, Fountoulakis, Kimon and Mahoney, Michael W. (2016). Parallel local graph clustering. In: Surajit Chaudhuri and Jayant Haritsa, Proceedings of the 42nd International Conference!on Very Large Data Bases. International Conferenceon Very Large Data Bases, New Delhi, India, (1041-1052). 5-9 September 2016. doi:10.14778/2994509.2994522

  • Xu, Peng, Yang, Jiyan, Roosta-Khorasani, Farbod, Re, Christopher and Mahoney, Michael (2016). Sub-sampled Newton methods with non-uniform sampling. In: D. D. Lee, M. Sugiyama, U. V. Luxburg, I. Guyon and R. Garnett, Advances in Neural Information Processing Systems 30. Neural Information Processing Systems 2016, Barcelona Spain, (2530-2538). 5 - 10 December 2016 .

Grants (Administered at UQ)

PhD and MPhil Supervision

Current Supervision

  • Doctor Philosophy — Principal Advisor

    Other advisors:

  • Doctor Philosophy — Principal Advisor

  • Doctor Philosophy — Associate Advisor

    Other advisors:

  • Doctor Philosophy — Associate Advisor

Completed Supervision