69 citations · 455 across the 44 of their papers we have counts for
5 papers · 1 filter
Edge rigidity and universality of random regular graphs of intermediate degree
Roland Bauerschmidt, Jiaoyang Huang, Antti Knowles +1
For random -regular graphs on vertices with , we develop a expansion of the local eigenvalue distribution about the Kesten-McKay law up to or…
Dynamics of Deep Neural Networks and Neural Tangent Hierarchy
Jiaoyang Huang, Horng-Tzer Yau
The evolution of a deep neural network trained by the gradient descent can be described by its neural tangent kernel (NTK) as introduced in [20], where it was proven that in the in…
Gradient Descent Finds Global Minima for Generalizable Deep Neural Networks of Practical Sizes
Kenji Kawaguchi, Jiaoyang Huang
In this paper, we theoretically prove that gradient descent can find a global minimum of non-convex optimization of all layers for nonlinear deep neural networks of sizes commonly…
Eigenvalues for the Minors of Wigner Matrices
Jiaoyang Huang
The eigenvalues for the minors of real symmetric () and complex Hermitian () Wigner matrices form the Wigner corner process, which is a multilevel interlacing particle sy…
Every Local Minimum Value is the Global Minimum Value of Induced Model in Non-convex Machine Learning
Kenji Kawaguchi, Jiaoyang Huang, Leslie Pack Kaelbling
For nonconvex optimization in machine learning, this article proves that every local minimum achieves the globally optimal value of the perturbable gradient basis model at any diff…