Constraining Variational Inference with Geometric Jensen-Shannon Divergence

Add to your list(s) Download to your calendar using vCal

• Jacob Deasy
• Tuesday 27 October 2020, 13:15-14:15
• Zoom.

If you have a question about this talk, please contact Mateja Jamnik.

Join us on Zoom

We examine the problem of controlling divergences for latent space regularisation in variational autoencoders. Specifically, when aiming to reconstruct example x∈ℝm via latent space z∈ℝn (n≤m), while balancing this against the need for generalisable latent representations. We present a regularisation mechanism based on the skew geometric-Jensen-Shannon divergence (JSGα). We find a variation in JSG α, motivated by limiting cases, which leads to an intuitive interpolation between forward and reverse KL in the space of both distributions and divergences. We motivate its potential benefits for VAEs through low-dimensional examples, before presenting quantitative and qualitative results. Our experiments demonstrate that skewing our variant of JSG α, in the context of JSG α-VAEs, leads to better reconstruction and generation when compared to several baseline VAEs. Our approach is entirely unsupervised and utilises only one hyperparameter which can be easily interpreted in latent space.

This talk is part of the Artificial Intelligence Research Group Talks (Computer Laboratory) series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Artificial Intelligence Research Group Talks (Computer Laboratory)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• Department of Computer Science and Technology talks and seminars
• Guy Emerson's list
• Hanchen DaDaDash
• Interested Talks
• School of Technology
• Speech Seminars
• Trust & Technology Initiative - interesting events
• Zoom
• bld31
• ndk22's list
• ob366-ai4er
• rp587
• yk373's list
• yk449

Note that ex-directory lists are not shown.