Vector quantization by deterministic annealing

By Kenneth M. Rose, E. Gurewitz, G. Fox. 1992

How researchers see this paper

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

Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations (2017, methodology): “Formally related but motivated from a probabilistic perspective are deterministic annealing methods for maximum entropy clustering/vector quantization, see, e.g. , [24, 42].”
Soft-to-Hard Vector Quantization for End-to-End Learned Compression of Images and Neural Networks (2017, methodology): “Arguably most related to our approach is (Wohlhart et al., 2013), which also employs continuation for nearest neighbor assignments, but in the context of learning a supervised prototype classifier.”
Deterministic annealing for clustering, compression, classification, regression, and related optimization problems (1998, background): “Various earlier versions of the principled derivation of DA appeared in [86], [89], and [90].”
Semi-Supervised Text Classification Using EM (2006, methodology): “This insight is the one that drives the approach called deterministic annealing (Rose et al. [1992]), first used as a way to construct a hierarchy during unsupervised clustering.”
Semi-Supervised Learning (2019, unknown): “, Scudder [1965], Fralick [1967], Agrawala [1970]).”
Adaptive computation and machine learning (1998, methodology): “This insight is the one that drives the approach called deterministic annealing (Rose et al., 1992), first used as a way to construct a hierarchy during unsupervised clustering.”