Hanover
DppNet: Approximating Determinantal Point Processes with Deep Networks
Zelda E. Mariet, Yaniv Ovadia, Jasper Snoek
Neural Information Processing Systems http://nips.cc/
Learning Signed Determinantal Point Processes through the Principal Minor Assignment Problem
Neural Information Processing Systems http://nips.cc/
On Controllable Sparse Alternatives to Softmax
Anirban Laha, Saneem Ahmed Chemmengath, Priyanka Agrawal, Mitesh Khapra, Karthik Sankaranarayanan, Harish G. Ramaswamy
Converting an n-dimensional vector to a probability distribution over n objects isacommonly used component inmanymachine learning tasks likemulticlass classification,multilabelclassification,attentionmechanismsetc.
Leveraged volume sampling for linear regression
Michal Derezinski, Manfred K. K. Warmuth, Daniel J. Hsu
Pd i=1(1 li) (see (8)), whereli = x>i (X>X) 1xi isthei-thleveragescoreofX. Here, weshow(3).
c6b8c8d762da15fa8dbbdfb6baf9e260-Paper.pdf
Our natural gradient approach enables application of parallel filtering andsmoothing, further reducing thetemporal spancomplexitytobelogarithmic inthe number oftime steps.
