I am a final year PhD student at the Australian National University and CSIRO Data61, advised by Richard Nock. Before this, I received a BSc (Adv) in Pure Mathematics at the University of Sydney.
I work on both theoretical and practical aspects of Machine Learning with particular research interests in generative models, privacy and robustness. I am interested in building theoretical foundations and explaining empirical phenomena in deep learning. Research questions I typically answer involve
- How does the information-theoretic divergence between probability measures interact with the data and structure of the learning problem?
- How can we train machine learning models to be more robust against adversaries of varying degree?
- [01/21] New work titled "Regularized Policies are Reward Robust" was accepted to AISTATS2021. We build on the theory of regularizing policies beyond entropy with additional connections to regression losses in Q-learning.
- [11/20] New preprint on Risk-Monotonicity, which helps us understand instability in training and resolves an open problem posed at COLT2019.
- [09/20] "Distributional Robustness with IPMs and links to Regularization and GANs" was accepted to NeurIPS2020.
- [06/20] Our work "Optimal Continual Learning has Perfect Memory and is NP-Hard" was accepted to ICML2020.
- [01/20] Our work "Local Differential Privacy for Sampling" was accepted to AISTATS2020.
- [11/19] I gave a talk
at the Max Planck Institute for Empirical Inference. (slides)
- [10/19] Our work "A Primal-Dual Link between GANs and Autoencoders" was accepted to NeurIPS2019.
Regularized Policies are Reward Robust.
Hisham Husain, Kamil Ciosek and Ryota Tomioka.
- Distributional Robustness with IPMs and links to Regularization and GANs.
- Optimal Continual Learning has Perfect Memory and is NP-Hard.
Jeremias Knoblauch, Hisham Husain and Tom Diethe.
- Local Differential Privacy for Sampling.
Hisham Husain, Borja Balle, Zac Cranko and Richard Nock.
- A Primal-Dual Link between GANs and Autoencoders.
Hisham Husain, Richard Nock and Robert C. Williamson.
- Data Preprocessing to Mitigate Bias with Fair Boosted Mollifiers
Alexander Soen, Hisham Husain and Richard Nock.
Risk-Monotonicity in Statistical Learning
Zakaria Mhammedi and Hisham Husain.
hisham dot husain at anu dot edu dot au