One of the main concepts in quantum physics is a density matrix, which is a symmetric positive definite matrix of trace one. Finite probability distributions are a special case where the density matrix is restricted to be diagonal. Density matrices are mixtures of dyads, where a dyad has the form uu' for any any unit column vector u. These unit vectors are the elementary events of the generalized probability space. Perhaps the simplest case to see that something unusual is going on is the case of uniform density matrix, i.e. 1/n times identity. This matrix assigns probability 1/n to every unit vector, but of course there are infinitely many of them. The new normalization rule thus says that sum of probabilities over any orthonormal basis of directions is one. We develop a probability calculus based on these more general distributions that includes definitions of joints, conditionals and formulas that relate these, i.e. analogs of the theorem of total probability, various Bayes rules for the calculation of posterior density matrices, etc. The resulting calculus parallels the familiar 'classical' probability calculus and always retains the latter as a special case when all matrices are diagonal.
Whereas the classical Bayesian methods maintain uncertainty about which model is 'best', the generalization maintains uncertainty about which unit direction has the largest variance. Surprisingly the bounds also generalize: as in the classical setting we bound the negative log likelihood of the data by the negative log likelihood of the MAP estimator.
[1]
A. Holevo.
Statistical structure of quantum theory
,
2001
.
[2]
A. Gleason.
Measures on the Closed Subspaces of a Hilbert Space
,
1957
.
[3]
O. Seeberg.
Statistical Mechanics. — A Set of Lectures
,
1975
.
[4]
Charles R. Johnson,et al.
Matrix analysis
,
1985,
Statistical Inference for Engineers and Data Scientists.
[5]
Manfred K. Warmuth,et al.
Randomized PCA Algorithms with Regret Bounds that are Logarithmic in the Dimension
,
2006,
NIPS.
[6]
Thierry Paul,et al.
Quantum computation and quantum information
,
2007,
Mathematical Structures in Computer Science.
[7]
Marc Alexa,et al.
Linear combination of transformations
,
2002,
ACM Trans. Graph..
[8]
Gunnar Rätsch,et al.
Matrix Exponentiated Gradient Updates for On-line Learning and Bregman Projection
,
2004,
J. Mach. Learn. Res..
[9]
C. Caves,et al.
Quantum Bayes rule
,
2000,
quant-ph/0008113.
[10]
Joseph M. Renes,et al.
Gleason-Type Derivations of the Quantum Probability Rule for Generalized Measurements
,
2004
.
[11]
Manfred K. Warmuth.
A Bayes Rule for Density Matrices
,
2005,
NIPS.
[12]
Taku Komura,et al.
Topology matching for fully automatic similarity estimation of 3D shapes
,
2001,
SIGGRAPH.
[13]
C. Adami,et al.
Quantum extension of conditional probability
,
1999
.
[14]
B. Simon.
Functional integration and quantum physics
,
1979
.