I am a Lecturer in machine learning at the Electrical and Electronics Engineering Department at Imperial College. My research is at the boundary between theory and practice in machine learning, where the goal is to infer a functional relation between an "input" and "output" domain, given only a finite number of observations.
My main focus is to develop efficient algorithms for machine learning in contexts with "structured" data, ranging from multitask, learning-to-learn and structured prediction problems to name but a few. The underlying assumption guiding my research is that most real-world learning problems are often enriched by “structural information” (e.g. the similarity between separate learning problems, or the constraints imposed by a specific input-output domain). This structure can be leveraged to significantly reduce the complexity of the overall learning process leading to algorithms that learn faster and better than those that work in isolation.
I like to apply these methods to a variety of challenging applications, ranging from computer vision to robotics, bioinformatics or recommendation systems to name but a few.
Bio - In 2008 I graduated in Mathematics at the University of Roma Tre, Rome, Italy and in 2012 I obtained a PhD in humanoid robotics, computer vision and machine learning at the Italian Institute of Technology, Genova, Italy. I was a Postdoctoral fellow in Poggio Lab at the Massachusetts Institute of Technology from 2012 to 2016 and later a Research Associate at UCL from 2017-2018, where I am now Honorary Lecturer. In 2018 I became a Lecturer at the EEE Department at Imperial College.
et al., 2019, Leveraging low-rank relations between surrogate tasks in structured prediction, 36th International Conference on Machine Learning, Icml 2019, Vol:2019-June, Pages:7415-7444
Ciliberto C, Bach F, Rudi A, 2019, Localized Structured Prediction, Advances in Neural Information Processing Systems 32 (nips 2019), Vol:32, ISSN:1049-5258
et al., 2018, Differential Properties of Sinkhorn Approximation for Learning with Wasserstein Distance, Advances in Neural Information Processing Systems (neurips), Dec 2018, Montr\'eal, Canada
Ciliberto C, Rudi A, Rosasco L, 2016, A Consistent Regularization Approach for Structured Prediction, Advances in Neural Information Processing Systems 29 (nips 2016), Vol:29, ISSN:1049-5258
et al., 2015, Convex learning of multiple tasks and their structure, 32nd International Conference on Machine Learning, Icml 2015, Vol:2, Pages:1548-1557
et al., 2018, Manifold structured prediction, 32nd Conference on Neural Information Processing Systems (NIPS), Massachusetts Institute of Technology Press, ISSN:1049-5258
et al., 2018, Learning to learn around a common mean, Pages:10169-10179, ISSN:1049-5258
et al., 2017, Consistent Multitask Learning with Nonlinear Output Relations, 31st Conference on Neural Information Processing Systems (NIPS), NEURAL INFORMATION PROCESSING SYSTEMS (NIPS), ISSN:1049-5258