Publication

Export 154 results:
Filters: Author is Poggio, Tomaso  [Clear All Filters]
2024
Poggio, T. & Fraser, M. Compositional Sparsity of Learnable Functions. (2024).PDF icon CBMM-Memo-145.pdf (1.25 MB)
Poggio, T. & Fraser, M. Compositional sparsity of learnable functions. Bulletin of the American Mathematical Society 61, 438-456 (2024).
Gan, Y. & Poggio, T. For HyperBFs AGOP is a greedy approximation to gradient descent. (2024).PDF icon CBMM-Memo-148.pdf (1.06 MB)
Ziyin, L., Chuang, I., Galanti, T. & Poggio, T. Formation of Representations in Neural Networks. (2024).PDF icon CBMM-Memo-150.pdf (4.03 MB)
Pinto, A., Rangamani, A. & Poggio, T. On Generalization Bounds for Neural Networks with Low Rank Layers. (2024).PDF icon CBMM-Memo-151.pdf (697.31 KB)
Gan, Y., Galanti, T., Poggio, T. & Malach, E. On the Power of Decision Trees in Auto-Regressive Language Modeling. (2024).PDF icon CBMM-Memo-149.pdf (2.11 MB)
2023
Poggio, T. & Magrini, M. Cervelli menti algoritmi. 272 (Sperling & Kupfer, 2023). at <https://www.sperling.it/libri/cervelli-menti-algoritmi-marco-magrini>
Xu, M., Rangamani, A., Liao, Q., Galanti, T. & Poggio, T. Dynamics in Deep Classifiers trained with the Square Loss: normalization, low rank, neural collapse and generalization bounds. Research (2023). doi:10.34133/research.0024PDF icon research.0024.pdf (4.05 MB)
Rangamani, A., Lindegaard, M., Galanti, T. & Poggio, T. Feature learning in deep classifiers through Intermediate Neural Collapse. (2023).PDF icon Feature_Learning_memo.pdf (2.16 MB)
Rangamani, A., Rosasco, L. & Poggio, T. For interpolating kernel machines, minimizing the norm of the ERM solution maximizes stability. Analysis and Applications 21, 193 - 215 (2023).
Gan, Y. & Poggio, T. A Homogeneous Transformer Architecture. (2023).PDF icon CBMM Memo 143 v2 (1.1 MB)
Singhal, U. et al. How to Guess a Gradient. arXiv (2023). at <https://arxiv.org/abs/2312.04709>
Xu, M. et al. The Janus effects of SGD vs GD: high noise and low rank. (2023).PDF icon Updated with appendix showing empirically that the main results extend to deep nonlinear networks (2.95 MB)PDF icon Small updates...typos... (616.82 KB)
Galanti, T., Xu, M., Galanti, L. & Poggio, T. Norm-Based Generalization Bounds for Compositionally Sparse Neural Networks. (2023).PDF icon Norm-based bounds for convnets.pdf (1.2 MB)
Galanti, T., Xu, M., Galanti, L. & Poggio, T. Norm-based Generalization Bounds for Sparse Neural Networks. NeurIPS 2023 (2023). at <https://proceedings.neurips.cc/paper_files/paper/2023/file/8493e190ff1bbe3837eca821190b61ff-Paper-Conference.pdf>PDF icon NeurIPS-2023-norm-based-generalization-bounds-for-sparse-neural-networks-Paper-Conference.pdf (577.69 KB)
Galanti, T., Siegel, Z., Gupte, A. & Poggio, T. SGD and Weight Decay Provably Induce a Low-Rank Bias in Deep Neural Networks. (2023).PDF icon Low-rank bias.pdf (2.38 MB)
Han, Y., Poggio, T. & Cheung, B. System Identification of Neural Systems: If We Got It Right, Would We Know?. Proceedings of the 40th International Conference on Machine Learning, PMLR 202, 12430-12444 (2023).PDF icon han23d.pdf (797.48 KB)
2022
Poggio, T. How Deep Sparse Networks Avoid the Curse of Dimensionality: Efficiently Computable Functions are Compositionally Sparse. (2022).PDF icon v1.0 (984.15 KB)PDF icon v5.7 adding in context learning etc (1.16 MB)
Gupte, A., Banburski, A. & Poggio, T. PCA as a defense against some adversaries. (2022).PDF icon CBMM-Memo-135.pdf (2.58 MB)
Anselmi, F. & Poggio, T. Representation Learning in Sensory Cortex: a theory. IEEE Access 1 - 1 (2022). doi:10.1109/ACCESS.2022.3208603PDF icon Representation_Learning_in_Sensory_Cortex_a_theory.pdf (1.17 MB)
Galanti, T. & Poggio, T. SGD Noise and Implicit Low-Rank Bias in Deep Neural Networks. (2022).PDF icon Implicit Rank Minimization.pdf (1.76 MB)
Han, Y., Poggio, T. & Cheung, B. System identification of neural systems: If we got it right, would we know?. (2022).PDF icon CBMM-Memo-136.pdf (1.75 MB)
2021
Adler, A., Araya-Polo, M. & Poggio, T. Deep Learning for Seismic Inverse Problems: Toward the Acceleration of Geophysical Analysis Workflows. IEEE Signal Processing Magazine 38, 89 - 119 (2021).
Banburski, A., De La Torre, F., Pant, N., Shastri, I. & Poggio, T. Distribution of Classification Margins: Are All Data Equal?. (2021).PDF icon CBMM Memo 115.pdf (9.56 MB)PDF icon arXiv version (23.05 MB)
Xu, M. et al. Dynamics and Neural Collapse in Deep Classifiers trained with the Square Loss. (2021).PDF icon v1.0 (4.61 MB)PDF icon v1.4corrections to generalization section (5.85 MB)PDF icon v1.7Small edits (22.65 MB)

Pages