TOMASO POGGIO
Massachusetts Institute of Technology
H-index: 149
North America-United States
Top articles of TOMASO POGGIO
Title | Journal | Author(s) | Publication Date |
---|---|---|---|
Compositional Sparsity of Learnable Functions | Tomaso Poggio Maia Fraser | 2024/2/8 | |
Norm-based Generalization Bounds for Sparse Neural Networks | Advances in Neural Information Processing Systems | Tomer Galanti Mengjia Xu Liane Galanti Tomaso Poggio | 2024/2/13 |
System identification of neural systems: If we got it right, would we know? | Yena Han Tomaso A Poggio Brian Cheung | 2023/7/3 | |
Dynamics in deep classifiers trained with the square loss: Normalization, low rank, neural collapse, and generalization bounds | Research | Mengjia Xu Akshay Rangamani Qianli Liao Tomer Galanti Tomaso Poggio | 2023/3/8 |
The Janus effects of SGD vs GD: high noise and low rank | Mengjia Xu Tomer Galanti Akshay Rangamani Lorenzo Rosasco Tomaso Poggio | 2023/12/21 | |
SGD and Weight Decay Provably Induce a Low-Rank Bias in Deep Neural Networks | Tomer Galanti Zachary Siegel Aparna Gupte Tomaso Poggio | 2023/2/14 | |
How to guess a gradient | arXiv preprint arXiv:2312.04709 | Utkarsh Singhal Brian Cheung Kartik Chandra Jonathan Ragan-Kelley Joshua B Tenenbaum | 2023/12/7 |
For interpolating kernel machines, minimizing the norm of the ERM solution maximizes stability | Analysis and Applications | Akshay Rangamani Lorenzo Rosasco Tomaso Poggio | 2023/1/28 |
A Homogeneous Transformer Architecture | Yulu Gan Tomaso Poggio | 2023/9/18 | |
Norm-based generalization bounds for compositionally sparse neural networks | arXiv preprint arXiv:2301.12033 | Tomer Galanti Mengjia Xu Liane Galanti Tomaso Poggio | 2023/1/28 |
Feature learning in deep classifiers through intermediate neural collapse | Akshay Rangamani Marius Lindegaard Tomer Galanti Tomaso A Poggio | 2023/7/3 | |
How deep sparse networks avoid the curse of dimensionality: Efficiently computable functions are compositionally sparse | CBMM Memo | Tomaso Poggio | 2022 |
Achieving Adversarial Robustness in Deep Learning-Based Overhead Imaging | Dagen Braun Matthew Reisman Larry Dewell Andrzej Banburski-Fahey Arturo Deza | 2022/10/11 | |
Foundations of deep learning: Compositional sparsity of computable functions | Tomaso Poggio | 2022 | |
Compositional Sparsity: a framework for ML | Tomaso Poggio | 2022/10/10 | |
Neural-guided, bidirectional program search for abstraction and reasoning | Simon Alford Anshula Gandhi Akshay Rangamani Andrzej Banburski Tony Wang | 2022 | |
Deep classifiers trained with the square loss | Center for Brains, Minds and Machines (CBMM) Memo No | Mengjia Xu Akshay Rangamani Andrzej Banburski Qianli Liao Tomer Galanti | 2022/7/10 |
PCA as a defense against some adversaries | Gupta Aparne Andrzej Banburski Tomaso Poggio | 2022/3/30 | |
SGD noise and implicit low-rank bias in deep neural networks | Tomer Galanti Tomaso Poggio | 2022/3/28 | |
Iterative regularization in classification via hinge loss diagonal descent | arXiv preprint arXiv:2212.12675 | Vassilis Apidopoulos Tomaso Poggio Lorenzo Rosasco Silvia Villa | 2022/12/24 |