`

Timezone: »

 
Poster
Relevant sparse codes with variational information bottleneck
Matthew Chalk · Olivier Marre · Gasper Tkacik

Wed Dec 07 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #196 #None

In many applications, it is desirable to extract only the relevant aspects of data. A principled way to do this is the information bottleneck (IB) method, where one seeks a code that maximises information about a relevance variable, Y, while constraining the information encoded about the original data, X. Unfortunately however, the IB method is computationally demanding when data are high-dimensional and/or non-gaussian. Here we propose an approximate variational scheme for maximising a lower bound on the IB objective, analogous to variational EM. Using this method, we derive an IB algorithm to recover features that are both relevant and sparse. Finally, we demonstrate how kernelised versions of the algorithm can be used to address a broad range of problems with non-linear relation between X and Y.

Author Information

Matthew Chalk (IST Austria)
Olivier Marre (Institut de la vision)
Gasper Tkacik (Institute of Science and Technology Austria)

More from the Same Authors