
Sparse recovery of elliptic solvers from matrixvector products
In this work, we show that solvers of elliptic boundary value problems i...
read it

Uncertainty Quantification of the 4th kind; optimal posterior accuracyuncertainty tradeoff with the minimum enclosing ball
There are essentially three kinds of approaches to Uncertainty Quantific...
read it

Decision Theoretic Bootstrapping
The design and testing of supervised machine learning models combine two...
read it

Do ideas have shape? Plato's theory of forms as the continuous limit of artificial neural networks
We show that ResNets converge, in the infinite depth limit, to a general...
read it

Learning dynamical systems from data: a simple crossvalidation perspective
Regressing the vector field of a dynamical system from a finite number o...
read it

Competitive Mirror Descent
Constrained competitive optimization involves multiple agents trying to ...
read it

Sparse Cholesky factorization by KullbackLeibler minimization
We propose to compute a sparse approximate inverse Cholesky factor L of ...
read it

Deep regularization and direct training of the inner layers of Neural Networks with Kernel Flows
We introduce a new regularization method for Artificial Neural Networks ...
read it

Kernel Mode Decomposition and programmable/interpretable regression networks
Mode decomposition is a prototypical pattern recognition problem that ca...
read it

Kernel Flows: from learning kernels from data into the abyss
Learning can be seen as approximating an unknown function by interpolati...
read it

Denoising by thresholding operator adapted wavelets
Donoho and Johnstone proposed a method from reconstructing an unknown sm...
read it

Universal Scalable Robust Solvers from Computational Information Games and fast eigenspace adapted Multiresolution Analysis
We show how the discovery of robust scalable numerical solvers for arbit...
read it

Gamblets for opening the complexitybottleneck of implicit schemes for hyperbolic and parabolic ODEs/PDEs with rough coefficients
Implicit schemes are popular methods for the integration of time depende...
read it

Multigrid with rough coefficients and Multiresolution operator decomposition from Hierarchical Information Games
We introduce a nearlinear complexity (geometric and meshless/algebraic)...
read it
Houman Owhadi
verfied profile
Professor of Applied and Computational Mathematics and Control and Dynamical Systems, California
Homepage:
http://users.cms.caltech.edu/~owhadi/index.htm