A Approximate Sampling from k-DPP Marginals The final piece of the A

In view of this, Barthelmé et al. (2019) propose an approximation to k-DPPs valid for large-scale ground sets which has better numerical properties. L( h): H [0, 1] be a random variable. The first equality uses Proposition 4. The second equality uses Proposition 3 and the fact that the We decompose bound the game regret into the sum of player and sampler regret. D, then a learner player that plays SGD algorithm suffers at most regret O ( GD T) . For convex regression and classification models we use linear models.