We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Compression is at the heart of effective representation learning. However, lossy compression is typically achieved through simple parametric models like Gaussian noise to preserve analytic tractability, and the limitations this imposes on learning are largely unexplored. Further, the Gaussian prior assumptions in models such as variational autoencoders (VAEs) provide only an upper bound on the compression rate in general. We introduce a new noise channel, \emph{Echo noise}, that admits a simple, exact expression for mutual information for arbitrary input distributions. The noise is constructed in a data-driven fashion that does not require restrictive distributional assumptions. With its complex encoding mechanism and exact rate regularization, Echo leads to improved bounds on log-likelihood and dominates $β$-VAEs across the achievable range of rate-distortion trade-offs. Further, we show that Echo noise can outperform flow-based methods without the need to train additional distributional transformations.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1904.07199")
get_code_for_paper("1904.07199")
have("1904.07199")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1904.07199.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1904.07199)
Connect an agent — have() is free.