Pasadena, CA 91125
United States
California Institute of Technology (Caltech)
Machine Learning, Algorithmic Information Theory, Cluster- ing, Density Estimation, Kernel Methods, Minimum Description Length Principle (MDL), Compression, Similarity, The Loss Rank Principle (LoRP), Algorithmic Mutual Information (AMI), Normalized Inform
learning stochastic differential equations, times series forecasting, extrapolation, computational graph completion, kernel methods, Machine learning, stochastic differential equations, one-shot learning, learning dynamical systems, learning dynamical systems from data
Kolmogorov complexityAlgorithmic information theoryKernel methodsReproducing kernel Hilbert spacesGaussian processesPositive definite kernelsNormalized compression distanceDistance-to-kernel embedding (D2KE)Random Fourier fe
Gaussian Processes, Stochastic Navier Stokes
Data-driven dynamical systemsInvariant setsHausdorff distanceKernel methodsReproducing kernel Hilbert spaces (RKHS)Kernel flowsChaotic dynamical systemsVariational methods
Quasi-potential, kernel methods, rare events, large deviation theory
Kernel Methods, Diffusion Maps, Learning Kernels from Data
Kernel Learning, Generative Modelling, MMD, KSD
