Spectral Inference Networks: Unifying Spectral Methods With Deep Learning

By David Pfau, Stig Petersen, Ashish Agarwal, David G. T. Barrett, Kimberly L. Stachenfeld. 2018

10 citations recorded by the source corpus.

Subfields: Probabilistic & Bayesian Methods

How researchers see this paper

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

In Probabilistic & Bayesian Methods

1. S. M. Ali Eslami
2. Ali Razavi
3. George Tucker
4. Yifan Wu
5. Carl Doersch
6. Jeffrey De Fauw
7. Aäron van den Oord
8. A. Srinivas

Citations in the corpus

• Data-Efficient Image Recognition with Contrastive Predictive Coding (2019, background): “Although many of these self-supervised objectives formulate prediction in terms of missing pixel-level details such as context or color [14, 69, 46, 38, 64], another class of methods defines prediction in higher-level, learned representation spaces [25, 16, 47, 49, 51].”
• The Laplacian in RL: Learning Representations with Efficient Approximations (2018, methodology): “Approaches more similar to ours (Shaham et al., 2018; Pfau et al., 2018) optimize objectives similar to Eq.”