Government
Off-Policy Evaluation for Action-Dependent Non-Stationary Environments (Appendix) Contents
In Figure 9 we provide bias and MSE analysis of different algorithms on the domains that exhibit passive non-stationarity.
Learning from Few Samples: Transformation-Invariant SVMs with Composition and Locality at Multiple Scales
Particularly important is the ability to incorporate domain knowledge of invariances, e.g., translational invariance of images. Kernels based on the maximum similarity over a group of transformations are not generally positive definite. Perhaps it is for this reason that they have not been studied theoretically.
Learning from Few Samples: Transformation-Invariant SVMs with Composition and Locality at Multiple Scales
Particularly important is the ability to incorporate domain knowledge of invariances, e.g., translational invariance of images. Kernels based on the maximum similarity over a group of transformations are not generally positive definite. Perhaps it is for this reason that they have not been studied theoretically.
Formulating Robustness Against Unforeseen Attacks
Neural networks have impressive performance on a variety of datasets (LeCun et al., 1998; He et al., 2015; Krizhevsky et al., 2017; Everingham et al., 2010) but can be fooled by imperceptible
