![Page 1: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/1.jpg)
Applied Bayesian Nonparametrics
3. Infinite Hidden Markov Models
Tutorial at CVPR 2012Erik Sudderth Brown University
Work by E. Fox, E. Sudderth, M. Jordan, & A. Willsky AOAS 2011: A Sticky HDP-HMM with Application to Speaker Diarization IEEE TSP 2011 & NIPS 2008: Bayesian Nonparametric Inference of Switching Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta Processes
![Page 2: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/2.jpg)
Observations True mode sequence •! Markov switching models for time series data
•! Cluster based on underlying mode dynamics
Temporal Segmentation
Hidden Markov Model modes
observations
![Page 3: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/3.jpg)
Outline Temporal Segmentation !!How many dynamical modes?
!!Mode persistence
!!Complex local dynamics
!!Multiple time series
Spatial Segmentation
!! Ising and Potts MRFs
!!Gaussian processes
![Page 4: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/4.jpg)
Hidden Markov Models
Time
Mod
e
modes
observations
![Page 5: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/5.jpg)
Hidden Markov Models
Time modes
observations
![Page 6: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/6.jpg)
Hidden Markov Models
Time modes
observations
![Page 7: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/7.jpg)
Hidden Markov Models
Time modes
observations
![Page 8: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/8.jpg)
Issue 1: How many modes?
•! Dirichlet process (DP): !! Mode space of unbounded size !! Model complexity adapts to
observations
•! Hierarchical: !! Ties mode transition
distributions !! Shared sparsity
Time
Mod
e
Infinite HMM: Beal, et.al., NIPS 2002 HDP-HMM: Teh, et. al., JASA 2006
Hierarchical Dirichlet Process HMM
![Page 9: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/9.jpg)
•! Global transition distribution:!
HDP-HMM
sparsity of ! is shared
•! Mode-specific transition distributions:!
Hierarchical Dirichlet Process HMM
![Page 10: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/10.jpg)
Issue 2: Temporal Persistence
Hidden Markov Model
True mode sequence HDP-HMM inferred mode sequence
![Page 11: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/11.jpg)
Sticky HDP-HMM
Time
Mod
e
![Page 12: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/12.jpg)
Sticky HDP-HMM
mode-specific base measure
Increased probability of self-transition
sticky original
Infinite HMM: Beal, et.al., NIPS 2002
![Page 13: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/13.jpg)
Direct Assignment Sampler •! Marginalize:
!! Transition densities !! Emission parameters
•! Sequentially sample:
Conjugate base measure "" closed form
Chinese restaurant
prior likelihood
Collapsed Gibbs Sampler
Splits true mode, hard to
merge
![Page 14: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/14.jpg)
•! Approximate HDP: "! Average transition density "! (" transition densities)
•! Sample:
Blocked Resampling HDP-HMM weak limit approximation HDP-HMM weak limit approximation
•! Compute backwards messages:
•! Block sample as:
" Average transition density " (" transition densities)
![Page 15: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/15.jpg)
Results: Gaussian Emissions
Blocked sampler
HDP-HMM Sticky HDP-HMM
Sequential sampler
![Page 16: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/16.jpg)
Sticky HDP-HMM
HDP-HMM
Results: Fast Switching
Observations
True mode sequence
![Page 17: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/17.jpg)
Hyperparameters •! Place priors on hyperparameters and infer them from data •! Weakly informative priors •! All results use the same settings
hyperparameters
can be set using the data
Related self-transition parameter: Beal, et.al., NIPS 2002
![Page 18: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/18.jpg)
HDP-HMM: Multimodal Emissions
•! Approximate multimodal emissions with DP mixture
•! Temporal mode persistence disambiguates model
modes
mixture components
observations
![Page 19: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/19.jpg)
John Jane Bob John Bob
Ji l l
0 1 2 3 4 5 6 7 8 9 10
x 104
-30
-20
-10
0
10
20
30
40
Speaker Diarization
![Page 20: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/20.jpg)
Results: 21 meetings
Overall DER
Best DER
Worst DER
Sticky HDP-HMM 17.84% 1.26% 34.29% Non-Sticky HDP-HMM
23.91% 6.26% 46.95%
ICSI 18.37% 4.39% 32.23%
0 10 20 30 40 500
10
20
30
40
50
Sticky DERsIC
SI D
ERs
! "! #! $! %! &!!
"!
#!
$!
%!
&!
'()*+,-./01
234
'()*+,-./0
1
![Page 21: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/21.jpg)
Results: Meeting 1
Sticky DER = 1.26%
ICSI DER = 7.56%
![Page 22: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/22.jpg)
Results: Meeting 18
Sticky DER = 20.48%
ICSI DER = 22.00%
4.81%
![Page 23: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/23.jpg)
= set of dynamic parameters
Issue 3: Complex Local Dynamics
•! Discrete clusters may not accurately capture high-dimensional data
•! Autoregressive HMM: Discrete-mode switching of smooth observation dynamics
Switching Dynamical Processes
modes
observations
![Page 24: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/24.jpg)
Linear Dynamical Systems •! State space LTI model:
•! Vector autoregressive (VAR) process:
![Page 25: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/25.jpg)
Linear Dynamical Systems •! State space LTI model:
State space models
VAR processes
•! Vector autoregressive (VAR) process:
![Page 26: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/26.jpg)
Switching Dynamical Systems Switching linear dynamical system (SLDS):
Switching VAR process:
![Page 27: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/27.jpg)
HDP-AR-HMM and HDP-SLDS HDP-AR-HMM HDP-SLDS
![Page 28: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/28.jpg)
Dancing Honey Bees
![Page 29: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/29.jpg)
Honey Bee Results: HDP-AR(1)-HMM
Sequence 1 Sequence 2 Sequence 3
HDP-AR-HMM: 88.1% SLDS [Oh]: 93.4%
HDP-AR-HMM: 92.5% SLDS [Oh]: 90.2%
HDP-AR-HMM: 88.2% SLDS [Oh]: 90.4%
![Page 30: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/30.jpg)
Issue 4: Multiple Time Series
•! Goal: !!Transfer knowledge between related time series !!Allow each system to switch between an
arbitrarily large set of dynamical modes •! Method:
!!Beta process prior !!Predictive distribution: Indian buffet process
![Page 31: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/31.jpg)
IBP-AR-HMM •! Latent features determine
which dynamical modes are used
•! Beta process prior: !! Encourages sharing !! Unbounded features
Features/Modes
Sequ
ence
s
!
![Page 32: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/32.jpg)
Motion Capture
CMU MoCap: http://mocap.cs.cmu.edu/ 6 videos of exercise routines:
![Page 33: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/33.jpg)
Library of MoCap Behaviors
![Page 34: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/34.jpg)
!"#$%&'()*+$,-'-.*'$ /0122*$*'$-34$05$678$
!"#$%&'()#*(*+,-#."#/0(1#'+23#0'2%4'#2+*'5(067#8+*'5(06#,+9',)#:(*#40($%&'&#*(#;<=>??7#@')A,*)#/0(1#>A53')#B#CA&&'0*3-#<D8E#F(0G)3(4-#8E<@#H".H7#
![Page 35: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/35.jpg)
!"#$%&'()'!)%&*+)+,#-.+/)
,&.(19*2*:$%&'()*+$;*)-9&12.$
I(2+*%(:)#(/#)','2*#9'3+$%(0)#+20())#+,,#$%&'()#
![Page 36: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/36.jpg)
!"#$%&'()'!)%&*+)+,#-.+/)
<&=)'$>?&'()$<0(*(2(,#0'JA%0')#)K%*23%:5#,%53*#(:L(//#+*#)*+0*#+:&#M%:%)3#
,&.(19*2*:$%&'()*+$;*)-9&12.$
![Page 37: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/37.jpg)
!"#$%&'()'!)%&*+)+,#-.+/)
@A*+$B2&:=*$<%NN+#:''&)#23'')'-#C+:&K%23#:''&)#O',,6#*(#9'5%:#40'4+0+*%(:#
,&.(19*2*:$%&'()*+$;*)-9&12.$
![Page 38: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/38.jpg)
!"#$%&'()'!)%&*+)+,#-.+/)
>*'$@9*+$;(*3#<%NN+)#+:&#;0(K:%')#:''&#*(#9'#9+G'&#*(#2(:2,A&'#40'4+0+*%(:#
,&.(19*2*:$%&'()*+$;*)-9&12.$
![Page 39: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/39.jpg)
!"#$%&'()'!)%&*+)+,#-.+/)
C2-'*$!)**.*$D:,6#%:#<%NN+#E%&'()#
,&.(19*2*:$%&'()*+$;*)-9&12.$
![Page 40: Applied Bayesian Nonparametrics 3. Infinite Hidden …sudderth/bnpCVPR12/slides/BNP3hdphmm.pdf · Dynamic Linear Models NIPS 2009: Sharing Features among Dynamical Systems with Beta](https://reader031.vdocuments.net/reader031/viewer/2022022018/5b87fb677f8b9a3d028c4d8f/html5/thumbnails/40.jpg)
!"#$%&'()'!)%&*+)+,#-.+/)
>'&2$;1?3$P:%JA'#*(#;0(K:%')-#9A*#1A,*%4,'#)*6,')#'Q%)*R#C*+99%:5#$)7#)K%0,%:5-#'*27#
,&.(19*2*:$%&'()*+$;*)-9&12.$