All Publications

2025

CBMM Memo No.
159
D. A. Danhofer, D’Ascenzo, D., Dubach, R., and Poggio, T., “Position: A Theory of Deep Learning Must Include Compositional Sparsity”. 2025.PDF icon CBMM Memo 159.pdf (676.35 KB)
CBMM Funded
CBMM Memo No.
158
R. Dubach, Abdallah, M. S., and Poggio, T., “Multiplicative Regularization Generalizes Better Than Additive Regularization”. 2025.PDF icon CBMM Memo 158.pdf (4.8 MB)
CBMM Funded
CBMM Memo No.
156
T. A. Poggio and Xu, M., “On efficiently computable functions, deep networks and sparse compositionality”. 2025.PDF icon Deep_sparse_networks_approximate_efficiently_computable_functions.pdf (223.15 KB)
CBMM Funded
S. Bono, Madan, S., Grover, I., Yasueda, M., Breazeal, C., Pfister, H., and Kreiman, G., “The Indoor-Training Effect: unexpected gains from distribution shifts in the transition function”. 2025.
CBMM Related
K. Tiwary, Young, A., Tasneem, Z., Klinghoffer, T., Dave, A., Poggio, T., Nilsson, D. - E., Cheung, B., and Raskar, R., “What if Eye..? Computationally Recreating Vision Evolution”, arXiv, 2025.PDF icon 2501.15001v1.pdf (5.2 MB)
CBMM Funded

2024

CBMM Memo No.
152
Q. Liao, Ziyin, L., Gan, Y., Cheung, B., Harnett, M., and Poggio, T., “Self-Assembly of a Biologically Plausible Learning Circuit”. 2024.PDF icon CBMM-Memo-152.pdf (1.84 MB)
CBMM Funded
CBMM Memo No.
151
A. Pinto, Rangamani, A., and Poggio, T., “On Generalization Bounds for Neural Networks with Low Rank Layers”. 2024.PDF icon CBMM-Memo-151.pdf (697.31 KB)
CBMM Funded
CBMM Memo No.
150
L. Ziyin, Chuang, I., Galanti, T., and Poggio, T., “Formation of Representations in Neural Networks”. 2024.PDF icon CBMM-Memo-150.pdf (4.03 MB)
CBMM Funded
CBMM Memo No.
149
Y. Gan, Galanti, T., Poggio, T., and Malach, E., “On the Power of Decision Trees in Auto-Regressive Language Modeling”. 2024.PDF icon CBMM-Memo-149.pdf (2.11 MB)
CBMM Funded
CBMM Memo No.
148
Y. Gan and Poggio, T., “For HyperBFs AGOP is a greedy approximation to gradient descent”. 2024.PDF icon CBMM-Memo-148.pdf (1.06 MB)
CBMM Funded
S. Madan, Xiao, W., Cao, M., Pfister, H., Livingstone, M. S., and Kreiman, G., “Benchmarking Out-of-Distribution Generalization Capabilities of DNN-based Encoding Models for the Ventral Visual Cortex”, in NeurIPS 2024, 2024.
CBMM Related
T. Poggio and Fraser, M., “Compositional sparsity of learnable functions”, Bulletin of the American Mathematical Society, vol. 61, pp. 438-456, 2024.
CBMM Funded
CBMM Memo No.
145
T. Poggio and Fraser, M., “Compositional Sparsity of Learnable Functions”. 2024.PDF icon This is an update of the AMS paper (230.72 KB)
CBMM Funded
P. Didier Alfano, Pastore, V. Paolo, Rosasco, L., and Odone, F., “Top-tuning: A study on transfer learning for an efficient alternative to fine tuning for image classification with fast kernel methods”, Image and Vision Computing, vol. 142, p. 104894, 2024.
CBMM Related
B. Peters, DiCarlo, J. J., Gureckis, T., Haefner, R., Isik, L., Tenenbaum, J., Konkle, T., Naselaris, T., Stachenfeld, K., Tavares, Z., Tsao, D., Yildirim, I., and Kriegeskorte, N., “How does the primate brain combine generative and discriminative computations in vision?”, arXiv, 2024.

2023

CBMM Memo No.
144
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.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)
CBMM Funded
T. Galanti, Xu, M., Galanti, L., and Poggio, T., “Norm-based Generalization Bounds for Sparse Neural Networks”, in NeurIPS 2023, New Orleans, 2023.PDF icon NeurIPS-2023-norm-based-generalization-bounds-for-sparse-neural-networks-Paper-Conference.pdf (577.69 KB)
CBMM Funded
G. Gaziv, Lee, M. J., and DiCarlo, J. J., “Strong and Precise Modulation of Human Percepts via Robustified ANNs”, in NeurIPS 2023, 2023.
CBMM Funded
U. Singhal, Cheung, B., Chandra, K., Ragan-Kelley, J., Tenenbaum, J. B., Poggio, T., and Yu, S. X., “How to Guess a Gradient”, arXiv, 2023.
CBMM Funded
G. Gaziv, Lee, M. J., and DiCarlo, J. J., “Robustified ANNs Reveal Wormholes Between Human Category Percepts”, arXiv, 2023.
CBMM Funded
T. Poggio and Magrini, M., Cervelli menti algoritmi. Sperling & Kupfer, 2023, p. 272.
CBMM Funded
CBMM Memo No.
143
Y. Gan and Poggio, T., “A Homogeneous Transformer Architecture”. 2023.PDF icon CBMM Memo 143 v2 (1.1 MB)
CBMM Funded
Y. Han, Poggio, T., and 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, vol. 202. pp. 12430-12444, 2023.PDF icon han23d.pdf (797.48 KB)
CBMM Funded
CBMM Memo No.
142
Y. Xie, Li, Y., and Rangamani, A., “Skip Connections Increase the Capacity of Associative Memories in Variable Binding Mechanisms”. 2023.PDF icon CBMM-Memo-142.pdf (1.64 MB)
CBMM Funded
A. Zador, Escola, S., Richards, B., Ölveczky, B., Bengio, Y., Boahen, K., Botvinick, M., Chklovskii, D., Churchland, A., Clopath, C., DiCarlo, J., Ganguli, S., Hawkins, J., Körding, K., Koulakov, A., LeCun, Y., Lillicrap, T., Marblestone, A., Olshausen, B., Pouget, A., Savin, C., Sejnowski, T., Simoncelli, E., Solla, S., Sussillo, D., Tolias, A. S., and Tsao, D., “Catalyzing next-generation Artificial Intelligence through NeuroAIAbstract”, Nature Communications, vol. 14, no. 1, 2023.
CBMM Funded

Pages