In these six lectures, we examine what can be learnt about the behavior ...
We investigate the time complexity of SGD learning on fully-connected ne...
We study the spectrum of inner-product kernel matrices, i.e., n × n
matr...
It is currently known how to characterize functions that neural networks...
Recent empirical work has shown that hierarchical convolutional kernels
...
Despite their many appealing properties, kernel methods are heavily affe...
A number of machine learning tasks entail a high degree of invariance: t...
Consider the classical supervised learning problem: we are given data
(y...
For a certain scaling of the initialization of stochastic gradient desce...
We study the supervised learning problem under either of the following t...
We consider the problem of learning an unknown function f_ on the
d-dime...
We consider learning two layer neural networks using stochastic gradient...
A number of statistical estimation problems can be addressed by semidefi...
An important problem of reconstruction of diffusion network and transmis...