PhD Thesis: G. Canal. Feedback Coding for Efficient Interactive Machine Learning. Georgia Institute of Technology, 2021. [thesis]

Journal-style, peer-reviewed, conference publications (8 pages or longer)

H. Bai, G. Canal, X. Du, J. Kwon, R. Nowak, and Y. Li. Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection. In The 40th International Conference on Machine Learning (ICML), Honolulu, HI, July 2023. (Acceptance rate 28%). [paper]

G. Canal, B. Mason, R. K. Vinayak, and R. Nowak. One for All: Simultaneous Metric and Preference Learning over Multiple Users. In The 36th Conference on Neural Information Processing Systems (NeurIPS), New Orleans, LA, December 2022. (Acceptance rate 26%). [paper] [code]

G. Canal, M. Bloch, and C. Rozell. Feedback Coding for Active Learning. In The 24th International Conference on Artificial Intelligence and Statistics (AISTATS), April 2021. (Acceptance rate 30%). [paper] [code]

M. Connor, G. Canal, and C. Rozell. Variational Autoencoder with Learned Latent Structure. In The 24th International Conference on Artificial Intelligence and Statistics (AISTATS), April 2021. (Acceptance rate 30%). [paper]

M. O’Shaughnessy, G. Canal, M. Connor, M. Davenport, and C. Rozell. Generative Causal Explanations of Black-box Classifiers. In The 34th Conference on Neural Information Processing Systems (NeurIPS), December 2020. (Acceptance rate 20%). [paper]

G. Canal*, S. Fenu*, (equal contribution) and C. Rozell. Active Ordinal Querying for Tuplewise Similarity Learning. In AAAI Conference on Artificial Intelligence (AAAI), New York, NY, February 2020. Selected for oral presentation. (Acceptance rate 20%). [paper]

G. Canal, A. Massimino, M. A. Davenport, and C. J. Rozell. Active Embedding Search via Noisy Paired Comparisons. In The 36th International Conference on Machine Learning (ICML), Long Beach, CA, June 2019. Selected for long oral presentation. (Acceptance rate 23%). [paper] [code]

Journal articles

G. Canal, Y. Diaz-Mercado, M. Egerstedt, and C. Rozell. A Low-complexity Brain-computer Interface for High-complexity Robot Swarm Control. In IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2023. [paper]

Peer-reviewed conference publications

J. Zhang, Y. Chen, G. Canal, S. Mussmann, Y. Zhu, S. Du, K. Jamieson, and R. Nowak. LabelBench: A Comprehensive Framework for Benchmarking Label-Efficient Learning. In The 40th International Conference on Machine Learning DMLR Workshop, Honolulu, HI, July 2023. [paper]

G. Canal, M. Connor, J. Jin, N. Nadagouda, M. O’Shaughnessy, C. Rozell, and M. Davenport. The Picasso Algorithm for Bayesian Localization via Paired Comparisons in a Union of Subspaces Model. In 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). May 2020.

G. Canal*, M. O’Shaughnessy*, (equal contribution) C. Rozell, and M. Davenport. Joint Estimation of Trajectory and Dynamics from Paired Comparisons. In International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), Guadeloupe, West Indies, December 2019. [paper]

G. Canal, A. Massimino, M. A. Davenport, and C. J. Rozell. Active Embedding Search via Noisy Paired Comparisons. In Signal Processing with Adaptive Sparse Structured Representations (SPARS) Workshop, Toulouse, France, July 2019. Poster presentation.

G. Canal, S. Manivasagam, S. Liang, and C. J. Rozell. Interactive Object Segmentation with Noisy Binary Inputs. In Proceedings of the IEEE Global Conference on Signal and Information Processing (GlobalSIP), Anaheim, CA, November 2018. Poster presentation.

Conference abstracts

G. Canal, S. Fenu, A. Massimino, M. A. Davenport, and C. J. Rozell. Informative Ordinal Querying for Similarity Embedding Construction and Search. In Coordinated Science Laboratory Student Conference, Urbana, IL, February 2019. Poster presentation.

G. Canal, Y. Diaz-Mercado, M. Egerstedt, and C. J. Rozell. Controlling High-complexity Robotic Swarms with Low-complexity EEG Brain-computer Interfaces. In International BCI Meeting, Pacific Grove, CA, May 2018. Selected for oral presentation.

G. Canal, Y. Diaz-Mercado, M. Egerstedt, and C. Rozell. Controlling High-complexity Robotic swarms with Low-complexity EEG Brain-machine Interfaces. In Society for Neuroscience Annual Meeting, Washington, D.C., November 2017. Poster presentation.