# 80 ih xt qt ih xt xt qt 481 ih xt

This preview shows page 1. Sign up to view the full content.

This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: r all t: Ih (X¬t ; Qt ) ≥ I (Xt ; X¬t ), Ih (Qt ; Xt ) ≥ I (Xt ; X¬t ), and |DQ | ≥ 2I (Xt ;X¬t ) where Ih (X¬t ; Qt ) (resp. Ih (Qt ; Xt )) is the information transmission rate between X¬t and Qt (resp. Qt and Xt ) under an HMM, and I (Xt ; X¬t ) is the true information transmission rate between I (Xt ; X¬t ). Prof. Jeﬀ Bilmes EE596A/Winter 2013/DGMs – Lecture 4 - Jan 23rd, 2013 page 4-78 (of 239) HMMs HMMs as GMs Other HMM queries What HMMs can do MPE Summ Proof: HMMs Generative Accuracy Proof. Accurate HMM (i.e., zero KL-divergence from true distribution) implies I (X¬t ; Xt ) = Ih (X¬t ; Xt ). We expand Ih (X¬t ; Qt , Xt ) in two ways using the chain rule of mutual information: Ih (X¬t ; Qt , Xt ) (4.80) = Ih (X¬t ; Qt ) + Ih (X¬t ; Xt |Qt ) (4.81) = Ih (X¬t ; Xt ) + Ih (X¬t ; Qt |Xt ) (4.82) = I (X¬t ; Xt ) + Ih (X¬t ; Qt |Xt ) (4.83) The HMM conditional independence properties say that Ih (X¬t ; Xt |Qt ) = 0, implying Ih (X¬t ; Qt ) = I (X¬t ; Xt ) + Ih (X¬t ; Qt |Xt ) Prof. Jeﬀ Bilmes EE596A/Winter 2013/DGMs – Lecture 4 - Jan 23rd, 2013 (4.84) page 4-79 (of 239) HMMs HMMs as GMs Other HMM queries What HMMs can do MPE Summ Proof cont.: HMMs Generative Accuracy ... cont. or that Ih (X¬t ; Qt ) ≥ I (X¬t ; Xt ) (4.85) since Ih (X¬t ; Qt |Xt ) ≥ 0. This is the ﬁrst condition. Similarly, the quantity Ih (Xt ; Qt , X¬t ) may be expanded as follows: Ih (Xt ; Qt , X¬t ) (4.86) = Ih (Xt ; Qt ) + Ih (Xt ; X¬t |Qt ) (4.87) = I (Xt ; X¬t ) + Ih (Xt ; Qt |X¬t ) (4.88) Reasoning as above, this leads to Ih (Xt ; Qt ) ≥ I (Xt ; X¬t ), (4.89) the second condition. Prof. Jeﬀ Bilmes EE596A/Winter 2013/DGMs – Lecture 4 - Jan 23rd, 2013 page 4-80 (of 239) HMMs HMMs as GMs Other HMM queries What HMMs can do MPE Summ Proof cont.: HMMs Generative Accuracy ... cont. A sequence of inequalities establishes the third condition: log |DQ | ≥ H (Qt ) ≥ H (Qt ) − H (Qt |Xt ) = Ih (Qt ; Xt ) ≥ I (Xt ; X¬t ) so |DQ | ≥ 2I (Xt ;X¬t ) . This is a lower bound - the numer of states must have enough capacity so that it is not a bottleneck, at the very least! This could be quite large, and grow with T . r.h.s. I (Xt ; X¬t ) is upper bounded by H (X¬t ) which could be as bad as log |DX¬t | Prof. Jeﬀ Bilmes EE596A/Winter 2013/DGMs – Lecture 4 - Jan 23rd, 2013 page 4-81 (of 239) HMMs HMMs as GMs Other HMM queries What HMMs can do MPE Summ Nec. conds for HMMs Generative Accuracy Insuﬃcient states can lead to model inaccuracies (e.g., state duration distribution using a geometric rather than something more realistic, add states to improve duration distribution while sharing observation parameters) Observation density family must be rich enough (2nd inequality) Two bottlenecks: observation density (e.g., number of Components of a Gaussian mixture), and time-dependency (number of states). Prof. Jeﬀ Bilmes EE596A/Winter 2013/DGMs – Lecture 4 - Jan 23rd, 2013 page 4-82 (of 239) HMMs HMMs as GMs Other HMM queries What HMMs can do MPE Summ...
View Full Document

## This document was uploaded on 04/05/2014.

Ask a homework question - tutors are online