Few-shot learning via learning the representation, provably
This paper studies few-shot learning via representation learning, where one uses $ T $
source tasks with $ n_1 $ data per task to learn a representation in order to reduce the …
source tasks with $ n_1 $ data per task to learn a representation in order to reduce the …
Tensor methods in computer vision and deep learning
Tensors, or multidimensional arrays, are data structures that can naturally represent visual
data of multiple dimensions. Inherently able to efficiently capture structured, latent semantic …
data of multiple dimensions. Inherently able to efficiently capture structured, latent semantic …
Simultaneous denoising, deconvolution, and demixing of calcium imaging data
We present a modular approach for analyzing calcium imaging recordings of large neuronal
ensembles. Our goal is to simultaneously identify the locations of the neurons, demix …
ensembles. Our goal is to simultaneously identify the locations of the neurons, demix …
On the power of over-parametrization in neural networks with quadratic activation
We provide new theoretical insights on why over-parametrization is effective in learning
neural networks. For a $ k $ hidden node shallow network with quadratic activation and $ n …
neural networks. For a $ k $ hidden node shallow network with quadratic activation and $ n …
Collaborative filtering with graph information: Consistency and scalable methods
Low rank matrix completion plays a fundamental role in collaborative filtering applications,
the key idea being that the variables lie in a smaller subspace than the ambient space …
the key idea being that the variables lie in a smaller subspace than the ambient space …
Limitations of lazy training of two-layers neural network
We study the supervised learning problem under either of the following two models:(1)
Feature vectors xi are d-dimensional Gaussian and responses are yi= f*(xi) for f* an …
Feature vectors xi are d-dimensional Gaussian and responses are yi= f*(xi) for f* an …
Global optimality in neural network training
BD Haeffele, R Vidal - Proceedings of the IEEE Conference …, 2017 - openaccess.thecvf.com
The past few years have seen a dramatic increase in the performance of recognition
systems thanks to the introduction of deep networks for representation learning. However …
systems thanks to the introduction of deep networks for representation learning. However …
Multiscale optical Ca2+ imaging of tonal organization in mouse auditory cortex
Spatial patterns of functional organization, resolved by microelectrode mapping, comprise a
core principle of sensory cortices. In auditory cortex, however, recent two-photon Ca 2+ …
core principle of sensory cortices. In auditory cortex, however, recent two-photon Ca 2+ …
Homogeneous codes for energy-efficient illumination and imaging
Programmable coding of light between a source and a sensor has led to several important
results in computational illumination, imaging and display. Little is known, however, about …
results in computational illumination, imaging and display. Little is known, however, about …
Global optimality in tensor factorization, deep learning, and beyond
BD Haeffele, R Vidal - arXiv preprint arXiv:1506.07540, 2015 - arxiv.org
Techniques involving factorization are found in a wide range of applications and have
enjoyed significant empirical success in many fields. However, common to a vast majority of …
enjoyed significant empirical success in many fields. However, common to a vast majority of …