Free energy coding

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Evaluating Lossy Compression Rates of Deep Generative Models (2020, methodology): “The basic scheme was proposed by Wallace (1990); Hinton & Van Camp (1993), and later implemented by Frey & Hinton (1996).”
End-to-End Learnt Image Compression via Non-Local Attention Optimization and Improved Context Modeling (2019, unknown): “with bits-back algorithm [44] for lossless compression.”
Practical Lossless Compression with Latent Variables using Bits Back Coding (2019, methodology): “However there is a method, known as ‘bits back coding’ (Wallace, 1990; Hinton and Camp, 1993), ﬁrst introduced as a thought experiment, but later implemented in Frey and Hinton (1996) and Frey (1997), which can be used to extend those algorithms to cope with latent variables.”
Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variables (2019, methodology): “Frey & Hinton (1996) implement the bits-back theory on a single datapoint x using AC.”
HiLLoC: Lossless Image Compression with Hierarchical Latent Variable Models (2019, methodology): “The first implementation of bits back coding (Frey, 1997; Frey & Hinton, 1996) made use of first-infirst-out (FIFO) arithmetic coding (AC) (Witten et al., 1987).”
Latent Variable Models (2019, methodology): “The first implementation of bits back coding (Frey, 1997; Frey & Hinton, 1996) made use of first-infirst-out (FIFO) arithmetic coding (AC) (Witten et al., 1987).”