optimal classifier
02bf86214e264535e3412283e817deaa-AuthorFeedback.pdf
We thank the reviewers for their insightful feedback, and we appreciate the opportunity to improve our paper. We will1 address typos and notational inconsistencies in the updated version.2 Response to Reviewer 1:3 We would like to emphasize that Theorem 1 is the most important contribution of our paper due to its generality.4 By considering the set of all possible classifiers, it provides lower bounds on adversarial robustness for any pair of5 class-conditional distributions. As we show in our experimental results in Section 6, we are able to obtain lower bounds6 for arbitrary real-world datasets by constructing the empirical distribution for these. In our estimation, these results7 serve to provide theoretical validation for adversarial training for low perturbation budgets as well as to highlight the8 gap to optimality for higher budgets.9
Responsible AI (RAI) Games and Ensembles
In this work, we provide a general framework for studying these problems, which we refer to as Responsible AI (RAI) games .
Optimality of Message-Passing Architectures for Sparse Graphs
Furthermore, we prove a corresponding non-asymptotic result.
Discriminative Calibration: Check Bayesian
However, SBC has drawbacks: The test statistic is somewhat ad-hoc, interactions are difficult to examine, multiple testing is a challenge, and the resulting p-value is not a divergence metric.
On The Classification-Distortion-Perception Tradeoff
Dong Liu, Haochen Zhang, Zhiwei Xiong
Neural Information Processing Systems http://nips.cc/
0ebcc77dc72360d0eb8e9504c78d38bd-Paper.pdf
As a consequence, empirical risk minimizers generally perform very poorly in extreme regions. It is the purpose of this paper to develop a general framework for classification in the extremes.
We would like to emphasize that Theorem 1 is the most important contribution of our paper due to its generality
We thank the reviewers for their insightful feedback, and we appreciate the opportunity to improve our paper. We would like to emphasize that Theorem 1 is the most important contribution of our paper due to its generality. In the Gaussian case, our sample complexity result follows directly from the expression for the optimal loss. Finally, while Dohmatob's bounds become non-trivial only when the adversarial We will also add a clearer description of the "translate and pair in place" coupling. Comparisons with Sinha et al. are in Section 7 and we compare to Dohmatob above.