Worst-Case Risk Quantification under Distributional Ambiguity using Kernel Mean Embedding in Moment Problem.
Jia-Jie ZhuWittawat JitkrittumMoritz DiehlBernhard SchölkopfPublished in: CoRR (2020)
Keyphrases
- worst case
- laplacian eigenmaps
- average case
- upper bound
- graph embedding
- risk management
- lower bound
- risk assessment
- kernel function
- np hard
- greedy algorithm
- co occurrence
- running times
- kernel methods
- computational complexity
- approximation algorithms
- decision making
- support vector
- risk measures
- vector space
- kernel regression
- latent space
- convolution kernel
- feature space
- digital images
- kernel machines
- kernel pca
- reproducing kernel hilbert space
- high risk
- component analysis
- multiple kernel learning
- space complexity
- nonlinear dimensionality reduction
- decision makers
- zernike moments
- data embedding
- worst case analysis
- geodesic distance
- similarity function