Codes based on inaccurate source probabilities

By Edgar N. Gilbert. 1971

How researchers see this paper

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

1. Nitish Shirish Keskar
2. Richard Socher
3. Yoshua Bengio
4. L. Varshney
5. Caiming Xiong
6. Percy Liang
7. Sergey Levine
8. Quoc V. Le

Citations in the corpus

• Learning Discrete Distributions from Untrusted Batches (2017, background): “The problem of learning a discrete distribution given access to independent samples has been intensely studied over the past century (see, e.g. [Gil71, KT81] and the references therein).”
• Limits of Detecting Text Generated by Large-Scale Language Models (2020, background): “The second term DKL(P ||Q) can be interpreted as the excess information rate needed to represent a language using a mismatched probability distribution [26].”
• PAC-Bayesian Analysis of Co-clustering and Beyond (2010, background): “This problem, known as “histogram smoothing”, has received significant attention in statistics and information theory (Gilbert, 1971; Cover, 1972; Krichevskiy, 1998; Paninski, 2004).”