Publication

Export 34 results:
Filters: Author is Lorenzo Rosasco  [Clear All Filters]
2022
Montagna, F., Noceti, N., Rosasco, L., Zhang, K. & Locatello, F. Scalable Causal Discovery with Score Matching. NeurIPS 2022 (2022). at <https://openreview.net/forum?id=v56PHv_W2A>
2020
Rangamani, A., Rosasco, L. & Poggio, T. For interpolating kernel machines, the minimum norm ERM solution is the most stable. (2020).PDF icon CBMM_Memo_108.pdf (1015.14 KB)PDF icon Better bound (without inequalities!) (1.03 MB)
2019
Muecke, N., Neu, G. & Rosasco, L. Beating SGD Saturation with Tail-Averaging and Minibatching. Neural Information Processing Systems (NeurIPS 2019) (2019).PDF icon 9422-beating-sgd-saturation-with-tail-averaging-and-minibatching.pdf (389.35 KB)
Banburski, A. et al. Dynamics & Generalization in Deep Networks -Minimizing the Norm. NAS Sackler Colloquium on Science of Deep Learning (2019).
Pagliana, N. & Rosasco, L. Implicit Regularization of Accelerated Methods in Hilbert Spaces. Neural Information Processing Systems (NeurIPS 2019) (2019).PDF icon 9591-implicit-regularization-of-accelerated-methods-in-hilbert-spaces.pdf (451.14 KB)
Banburski, A. et al. Weight and Batch Normalization implement Classical Generalization Bounds . ICML (2019).
2018
Banburski, A. et al. Theory III: Dynamics and Generalization in Deep Networks. (2018).PDF icon Original, intermediate versions are available under request (2.67 MB)PDF icon CBMM Memo 90 v12.pdf (4.74 MB)PDF icon Theory_III_ver44.pdf Update Hessian (4.12 MB)PDF icon Theory_III_ver48 (Updated discussion of convergence to max margin) (2.56 MB)PDF icon fixing errors and sharpening some proofs (2.45 MB)
2017
Mutch, J. et al. Computational and Cognitive Neuroscience of Vision 85-104 (Springer, 2017).
Anselmi, F., Evangelopoulos, G., Rosasco, L. & Poggio, T. Symmetry Regularization. (2017).PDF icon CBMM-Memo-063.pdf (6.1 MB)
Poggio, T. et al. Theory of Deep Learning III: explaining the non-overfitting puzzle. (2017).PDF icon CBMM-Memo-073.pdf (2.65 MB)PDF icon CBMM Memo 073 v2 (revised 1/15/2018) (2.81 MB)PDF icon CBMM Memo 073 v3 (revised 1/30/2018) (2.72 MB)PDF icon CBMM Memo 073 v4 (revised 12/30/2018) (575.72 KB)
Poggio, T., Mhaskar, H., Rosasco, L., Miranda, B. & Liao, Q. Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A review. International Journal of Automation and Computing 1-17 (2017). doi:10.1007/s11633-017-1054-2PDF icon art%3A10.1007%2Fs11633-017-1054-2.pdf (1.68 MB)
2016
Nickel, M., Rosasco, L. & Poggio, T. Holographic Embeddings of Knowledge Graphs. Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16) (2016).PDF icon 1510.04935v2.pdf (360.65 KB)
Anselmi, F., Rosasco, L. & Poggio, T. On invariance and selectivity in representation learning. Information and Inference: A Journal of the IMA iaw009 (2016). doi:10.1093/imaiai/iaw009PDF icon imaiai.iaw009.full_.pdf (267.87 KB)
Poggio, T., Mhaskar, H., Rosasco, L., Miranda, B. & Liao, Q. Theory I: Why and When Can Deep Networks Avoid the Curse of Dimensionality?. (2016).PDF icon CBMM-Memo-058v1.pdf (2.42 MB)PDF icon CBMM-Memo-058v5.pdf (2.45 MB)PDF icon CBMM-Memo-058-v6.pdf (2.74 MB)PDF icon Proposition 4 has been deleted (2.75 MB)
2015
Anselmi, F., Rosasco, L., Tan, C. & Poggio, T. Deep Convolutional Networks are Hierarchical Kernel Machines. (2015).PDF icon CBMM Memo 035_rev5.pdf (975.65 KB)
Zhang, C., Voinea, S., Evangelopoulos, G., Rosasco, L. & Poggio, T. Discriminative Template Learning in Group-Convolutional Networks for Invariant Speech Representations. INTERSPEECH-2015 (International Speech Communication Association (ISCA), 2015). at <http://www.isca-speech.org/archive/interspeech_2015/i15_3229.html>
Nickel, M., Rosasco, L. & Poggio, T. Holographic Embeddings of Knowledge Graphs. (2015).PDF icon holographic-embeddings.pdf (677.87 KB)
Anselmi, F., Rosasco, L. & Poggio, T. On Invariance and Selectivity in Representation Learning. (2015).PDF icon CBMM Memo No. 029 (812.07 KB)
Poggio, T., Anselmi, F. & Rosasco, L. I-theory on depth vs width: hierarchical function composition. (2015).PDF icon cbmm_memo_041.pdf (1.18 MB)
Rosasco, L. & Villa, S. Learning with incremental iterative regularization. NIPS 2015 (2015). at <https://papers.nips.cc/paper/6015-learning-with-incremental-iterative-regularization>PDF icon Learning with Incremental Iterative Regularization_1405.0042v2.pdf (504.66 KB)
Rudi, A., Camoriano, R. & Rosasco, L. Less is More: Nyström Computational Regularization. NIPS 2015 (2015). at <https://papers.nips.cc/paper/5936-less-is-more-nystrom-computational-regularization>PDF icon Less is More- Nystr ̈om Computational Regularization_1507.04717v4.pdf (287.14 KB)
Poggio, T., Rosasco, L., Shashua, A., Cohen, N. & Anselmi, F. Notes on Hierarchical Splines, DCLNs and i-theory. (2015).PDF icon CBMM Memo 037 (1.83 MB)
Anselmi, F. et al. Unsupervised learning of invariant representations. Theoretical Computer Science (2015). doi:10.1016/j.tcs.2015.06.048
2014
Zhang, C., Evangelopoulos, G., Voinea, S., Rosasco, L. & Poggio, T. A Deep Representation for Invariance and Music Classification. ICASSP 2014 - 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE, 2014). doi:10.1109/ICASSP.2014.6854954
Zhang, C., Evangelopoulos, G., Voinea, S., Rosasco, L. & Poggio, T. A Deep Representation for Invariance And Music Classification. (2014).PDF icon CBMM-Memo-002.pdf (1.63 MB)

Pages