Neural Information Processing Systems http://nips.cc/

Whentheinputs associated Ex. 1), theterms

Neural Information Processing Systems http://nips.cc/

In recent years, machine learning models have been shown to be vulnerable to backdoor attacks.

Empirical data can often be considered as samples from a set of probability distributions.

Regression with group-sparsity penalty plays acentral role in high-dimensional predictionproblems.

More precisely, we study a Nyström approach to kernel k-means. Weanalyze thestatistical properties oftheproposed method andshow that it achieves the same accuracy of exact kernel k-means with only a fraction of computations.

We study the linear contextual bandit problem where an agent has to select one candidate from a pool and each candidate belongs to a sensitive group. In this setting,candidates' rewardsmaynotbedirectly comparable between groups,for example when the agent is an employer hiring candidates from different ethnic groups and some groups have a lower reward due to discriminatory bias and/or socialinjustice.