Lorenzo Rosasco

Lorenzo Rosasco
Lorenzo
Rosasco
Investigator
Italian Institute of Technology (IIT), Università degli Studi di Genova

Associated Research Module: 

Associated Research Thrust: 

Lorenzo Rosasco is  associate professor at  the University of Genova, Italy. He also holds a  research scientist at the Massachusetts Institute of Technology (MIT) and a collaborator position at the Istituto Italiano di Tecnologia (IIT). He is leading the efforts to establish the Laboratory for Computational and Statistical Learning (LCSL),  born from a collaborative agreement between IIT and MIT. He received his PhD from the University of Genova in 2006 where he worked under the supervision of Alessandro Verri and Ernesto De Vito in the SLIPGURU. He was a  visiting student with Tomaso Poggio at the Center for Biological and Computational Learning (CBCL) at MIT, and with Steve Smale at the Toyota Technological Institute at Chicago (TTI-Chicago.) Between  2006 and 2009 he was a postdoctoral fellow at CBCL working with Tomaso Poggio. His research focuses on studying theory and algorithms for machine learning. Dr. Rosasco has developed and analyzed methods to learn from small as well as large samples of high dimensional data, using analytical and probabilistic tools, within a multidisciplinary approach drawing concepts and techniques primarily from computer science but also from statistics, engineering and applied mathematics.

Website: 

Projects

Invariance and Selectivity in Representation Learning
Invariant Representation Learning for Speech Recognition

CBMM Publications

F. Montagna, Mastakouri, A. A., Eulig, E., Noceti, N., Rosasco, L., Janzing, D., Aragam, B., and Locatello, F., “Assumption violations in causal discovery and the robustness of score matching”, in 37th Conference on Neural Information Processing Systems (NeurIPS 2023), 2024.
E. Caldarelli, Chatalic, A., Colom´e, A. `a, Rosasco, L., and Torras, C., “Heteroscedastic Gaussian Processes and Random Features: Scalable Motion Primitives with Guarantees”, in 7th Conference on Robot Learning (CoRL 2023, Altanta, GA, 2023.
G. Meanti*, Chatalic, A., Kostic, V. R., Novelli, P., Pontil, M., and Rosasco, L., “Estimating Koopman operators with sketching to provably learn large scale dynamical systems”, in 37th Conference on Neural Information Processing Systems (NeurIPS 2023), 2023.
M. Rando, Molinari, C., Villa, S., and Rosasco, L., “An Optimal Structured Zeroth-order Algorithm for Non-smooth Optimization”, in 37th Conference on Neural Information Processing Systems (NeurIPS 2023), 2023.
M. Xu, Galanti, T., Rangamani, A., Rosasco, L., Pinto, A., and Poggio, T., “The Janus effects of SGD vs GD: high noise and low rank”. 2023.
F. Montagna, Noceti, N., Rosasco, L., Zhang, K., and Locatello, F., “Scalable Causal Discovery with Score Matching”, NeurIPS 2022. 2022.
A. Rangamani, Rosasco, L., and Poggio, T., “For interpolating kernel machines, the minimum norm ERM solution is the most stable”. 2020.
A. Banburski, Liao, Q., Miranda, B., Rosasco, L., Hidary, J., and Poggio, T., “Dynamics & Generalization in Deep Networks -Minimizing the Norm”, in NAS Sackler Colloquium on Science of Deep Learning, Washington D.C., 2019.
A. Banburski, Liao, Q., Miranda, B., Rosasco, L., Hidary, J., and Poggio, T., “Weight and Batch Normalization implement Classical Generalization Bounds ”, in ICML, Long Beach/California, 2019.
N. Muecke, Neu, G., and Rosasco, L., “Beating SGD Saturation with Tail-Averaging and Minibatching”, Neural Information Processing Systems (NeurIPS 2019). Vancouver, Canada, 2019.
N. Pagliana and Rosasco, L., “Implicit Regularization of Accelerated Methods in Hilbert Spaces”, Neural Information Processing Systems (NeurIPS 2019). Vancouver, Canada, 2019.
A. Banburski, Liao, Q., Miranda, B., Poggio, T., Rosasco, L., Hidary, J., and De La Torre, F., “Theory III: Dynamics and Generalization in Deep Networks”. 2018.
J. Mutch, Anselmi, F., Tacchetti, A., Rosasco, L., Leibo, J. Z., and Poggio, T., “Invariant Recognition Predicts Tuning of Neurons in Sensory Cortex”, in Computational and Cognitive Neuroscience of Vision, Springer, 2017, pp. 85-104.
T. Poggio, Mhaskar, H., Rosasco, L., Miranda, B., and Liao, Q., “Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A review”, International Journal of Automation and Computing, pp. 1-17, 2017.
F. Anselmi, Evangelopoulos, G., Rosasco, L., and Poggio, T., “Symmetry Regularization”. 2017.
T. Poggio, Kawaguchi, K., Liao, Q., Miranda, B., Rosasco, L., Boix, X., Hidary, J., and Mhaskar, H., “Theory of Deep Learning III: explaining the non-overfitting puzzle”. 2017.
M. Nickel, Rosasco, L., and Poggio, T., “Holographic Embeddings of Knowledge Graphs”, in Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16), Phoenix, Arizona, USA, 2016.
F. Anselmi, Rosasco, L., and Poggio, T., “On invariance and selectivity in representation learning”, Information and Inference: A Journal of the IMA, p. iaw009, 2016.
T. Poggio, Mhaskar, H., Rosasco, L., Miranda, B., and Liao, Q., “Theory I: Why and When Can Deep Networks Avoid the Curse of Dimensionality?”. 2016.
A. Rudi, Camoriano, R., and Rosasco, L., “Less is More: Nyström Computational Regularization”, in NIPS 2015, 2015.
T. Poggio, Rosasco, L., Shashua, A., Cohen, N., and Anselmi, F., “Notes on Hierarchical Splines, DCLNs and i-theory”. 2015.
L. Rosasco and Villa, S., “Learning with incremental iterative regularization”, in NIPS 2015, 2015.
F. Anselmi, Rosasco, L., and Poggio, T., “On Invariance and Selectivity in Representation Learning”. 2015.
F. Anselmi, Rosasco, L., Tan, C., and Poggio, T., “Deep Convolutional Networks are Hierarchical Kernel Machines”. 2015.
F. Anselmi, Leibo, J. Z., Rosasco, L., Mutch, J., Tacchetti, A., and Poggio, T., “Unsupervised learning of invariant representations”, Theoretical Computer Science, 2015.
C. Zhang, Voinea, S., Evangelopoulos, G., Rosasco, L., and Poggio, T., “Discriminative Template Learning in Group-Convolutional Networks for Invariant Speech Representations”, in INTERSPEECH-2015, Dresden, Germany, 2015.
M. Nickel, Rosasco, L., and Poggio, T., “Holographic Embeddings of Knowledge Graphs”. 2015.
T. Poggio, Anselmi, F., and Rosasco, L., “I-theory on depth vs width: hierarchical function composition”. 2015.
S. Voinea, Zhang, C., Evangelopoulos, G., Rosasco, L., and Poggio, T., “Word-level Invariant Representations From Acoustic Waveforms”, in INTERSPEECH 2014 - 15th Annual Conf. of the International Speech Communication Association, Singapore, 2014.
C. Zhang, Voinea, S., Evangelopoulos, G., Rosasco, L., and Poggio, T., “Phone Classification by a Hierarchy of Invariant Representation Layers”, in INTERSPEECH 2014 - 15th Annual Conf. of the International Speech Communication Association, Singapore, 2014.
C. Zhang, Evangelopoulos, G., Voinea, S., Rosasco, L., and Poggio, T., “A Deep Representation for Invariance And Music Classification”. 2014.
F. Anselmi, Leibo, J. Z., Rosasco, L., Mutch, J., Tacchetti, A., and Poggio, T., “Unsupervised learning of invariant representations with low sample complexity: the magic of sensory cortex or a new framework for machine learning?”. 2014.
C. Zhang, Evangelopoulos, G., Voinea, S., Rosasco, L., and Poggio, T., “A Deep Representation for Invariance and Music Classification”, in ICASSP 2014 - 2014 IEEE International Conference on Acoustics, Speech and Signal Processing, Florence, Italy, 2014.
G. Evangelopoulos, Voinea, S., Zhang, C., Rosasco, L., and Poggio, T., “Learning An Invariant Speech Representation”. 2014.
S. Voinea, Zhang, C., Evangelopoulos, G., Rosasco, L., and Poggio, T., “Speech Representations based on a Theory for Learning Invariances”. SANE 2014 - Speech and Audio in the Northeast, 2014.
S. Villa, Rosasco, L., Poggio, T., Schölkopf, B., Luo, Z., and Vovk, V., “On Learnability, Complexity and Stability”, in Empirical Inference, Berlin, Heidelberg: Springer Berlin Heidelberg, 2013, pp. 59 - 69.
L. Rosasco, “Object recognition data sets (iCub/IIT)”. 2013.
F. Anselmi, Leibo, J. Z., Rosasco, L., Mutch, J., Tacchetti, A., and Poggio, T., “Unsupervised Learning of Invariant Representations in Hierarchical Architectures.”. 2013.
G. D. Canas, Poggio, T., and Rosasco, L., “Learning manifolds with k-means and k-flats”, in Advances in Neural Information Processing Systems 25 (NIPS 2012), 2012.