
When Do Neural Networks Outperform Kernel Methods?
For a certain scaling of the initialization of stochastic gradient desce...
read it

The generalization error of random features regression: Precise asymptotics and double descent curve
Deep learning methods operate in regimes that defy the traditional stati...
read it

Limitations of Lazy Training of Twolayers Neural Networks
We study the supervised learning problem under either of the following t...
read it

Linearized twolayers neural networks in high dimension
We consider the problem of learning an unknown function f_ on the ddime...
read it

Proximal algorithms for constrained composite optimization, with applications to solving lowrank SDPs
We study a family of (potentially nonconvex) constrained optimization p...
read it

Meanfield theory of twolayers neural networks: dimensionfree bounds and kernel limit
We consider learning two layer neural networks using stochastic gradient...
read it

TAP free energy, spin glasses, and variational inference
We consider the SherringtonKirkpatrick model of spin glasses with ferro...
read it

A Mean Field View of the Landscape of TwoLayers Neural Networks
Multilayer neural networks are among the most powerful models in machin...
read it

The landscape of the spiked tensor model
We consider the problem of estimating a large rankone tensor u^⊗ k∈( R...
read it

Solving SDPs for synchronization and MaxCut problems via the Grothendieck inequality
A number of statistical estimation problems can be addressed by semidefi...
read it

The Landscape of Empirical Risk for Nonconvex Losses
Most highdimensional estimation and prediction methods propose to minim...
read it
Song Mei
is this you? claim profile