part iii latent tree models
play

Part III: Latent Tree Models Le Song ICML 2012 Tutorial on Spectral - PowerPoint PPT Presentation

Sep 02, 2022 β€’142 likes β€’548 views

Spectral Algorithms for Latent Variable Models Part III: Latent Tree Models Le Song ICML 2012 Tutorial on Spectral Algorithms for Latent Variable Models, Edinburgh, UK Joint work with Mariya Ishteva, Ankur Parikh, Eric Xing, Byron Boots , Geoff

  1. Spectral Algorithms for Latent Variable Models Part III: Latent Tree Models Le Song ICML 2012 Tutorial on Spectral Algorithms for Latent Variable Models, Edinburgh, UK Joint work with Mariya Ishteva, Ankur Parikh, Eric Xing, Byron Boots , Geoff Gordon, Alex Smola and Kenji Fukumizu

  2. Latent Tree Graphical Models Graphical model: nodes represent variables, edges represent conditional independence relation Latent tree graphical models: latent and observed variables are arranged in a tree structure Latent Variable Observed Variable π‘Œ 10 Latent Tree Hidden Markov Model π‘Œ 7 π‘Œ 8 π‘Œ 9 π‘Œ 10 π‘Œ 11 π‘Œ 12 π‘Œ 7 π‘Œ 8 π‘Œ 9 π‘Œ 1 π‘Œ 2 π‘Œ 3 π‘Œ 4 π‘Œ 5 π‘Œ 6 π‘Œ 1 π‘Œ 2 π‘Œ 3 π‘Œ 4 π‘Œ 5 π‘Œ 6 Many real world applications, eg., time-series prediction, topic modeling 2

  3. Scope of This Tutorial Estimating marginal probability of the observed variables Spectral HMMs (Hsu et al. COLT’09) Kernel spectral HMMs (Song et al. ICML’10) Spectral latent tree (Parikh et al. ICML’11, Song et al. NIPS’11) Spectral dimensional reduction for HMMs (Foster et al. Arxiv) More recent: Cohen et al. ACL’12, Balle et al. ICML’12 Estimating latent parameters PCA approach (Mossel & Roch AOAP’06) PCA and SVD approach, (Anandkumar et al. COLT’12, Arxiv) Estimating the structure of latent variable models Recursive grouping (Choi et al. JMLR’11) Spectral short quartet (Anandkumar et al. NIPS’11) 3

  4. Challenge of Estimating Marginal of Observed Variables Exponential number of entries in 𝑄 π‘Œ 1 , π‘Œ 2 , … , π‘Œ 6 Discrete variable taking π‘œ possible values, 𝑄 has 𝑃(π‘œ 6 ) entries! Latent tree reduces the number of parameters 𝑄 π‘Œ 1 , π‘Œ 2 , … , π‘Œ 6 = 𝑄 π‘Œ 1 , π‘Œ 2 , … , π‘Œ 6 , 𝑦 7 , … , 𝑦 10 𝑃 3π‘œ 2 𝑦 7 ,𝑦 8 ,𝑦 9 ,𝑦 10 𝑃 π‘œ params params 𝑄 π‘Œ 10 𝑄 𝑦 7 𝑦 10 𝑄 π‘Œ 1 𝑦 7 𝑄 π‘Œ 2 𝑦 7 π‘Œ 10 𝑦 7 ,𝑦 8 ,𝑦 9 ,𝑦 10 𝑄 𝑦 8 𝑦 10 𝑄 π‘Œ 3 𝑦 8 𝑄(π‘Œ 4 |𝑦 8 ) 𝑄 𝑦 9 𝑦 10 𝑄 π‘Œ 5 𝑦 9 𝑄(π‘Œ 6 |𝑦 9 ) π‘Œ 9 π‘Œ 7 π‘Œ 8 Latent tree has 𝑃 9π‘œ 2 params π‘Œ 1 π‘Œ 2 π‘Œ 3 π‘Œ 4 π‘Œ 5 π‘Œ 6 Significant saving! 4

  5. EM Algorithm for Parameter Estimation Do not observe latent variables, need to estimate the corresponding parameters, eg., 𝑄(π‘Œ 7 |π‘Œ 10 ) and 𝑄 π‘Œ 1 π‘Œ 7 π‘Œ 10 Goal of spectral algorithm: π‘Œ 7 π‘Œ 8 π‘Œ 9 Estimate the marginal in π‘Œ 1 π‘Œ 2 π‘Œ 3 π‘Œ 4 π‘Œ 5 π‘Œ 6 local-minimum-free fashion 1 1 1 1 1 1 𝑗 = 1 𝑦 1 𝑦 2 𝑦 3 𝑦 4 𝑦 6 𝑦 5 … … … 𝑛 𝑛 𝑛 𝑛 𝑛 𝑛 𝑗 = 𝑛 𝑦 2 𝑦 3 𝑦 1 𝑦 4 𝑦 5 𝑦 6 Expectation maximization: maximize likelihood of observations 𝑛 𝑗 , … , 𝑦 6 𝑗 ) max 𝑄(𝑦 1 𝑗=1 Drawback: local maxima, slow to converge, difficult to analyze 5

  6. Key Features of Spectral Algorithms Represent joint probability table of observed variables with low rank factorization, without using the joint table in the computation! Eg. 𝑄 1,…,𝑒 ; 𝑒+1 ,…,2𝑒 = π‘†π‘“π‘‘β„Žπ‘π‘žπ‘“(𝑄 π‘Œ 1 , … , π‘Œ 2𝑒 , 1, … , 𝑒 ) π‘œ 𝑒 β€’ Represent it by low rank factors to avoid exponential blowup β€’ Use clever decomposition π‘œ 𝑒 𝑄 1,…,𝑒 ; 𝑒+1 ,…,2𝑒 technique to avoid directly using all entries from the table β€’ Use singular value decomposition 6

  7. Tensor View of Marginal Probability Marginal probability table 𝓀 = 𝑄 π‘Œ 1 , π‘Œ 2 , … , π‘Œ 6 Discrete variable taking π‘œ possible values 1, … , π‘œ 6-way table, or 6 th order tensor Dimension labeled by the variable Value of the variable is the index to the corresponding dimension, need 6 indexes to access a single entry 𝑄(π‘Œ 1 = 1, π‘Œ 2 = 4, … , π‘Œ 6 = 3) is the entry 𝓀[1,4, … , 3] Running Examples: Latent Tree π‘Œ 10 π‘Œ 7 π‘Œ 8 π‘Œ 9 π‘Œ 10 π‘Œ 11 π‘Œ 12 Hidden Markov π‘Œ 7 π‘Œ 8 π‘Œ 9 Model π‘Œ 1 π‘Œ 2 π‘Œ 3 π‘Œ 4 π‘Œ 5 π‘Œ 6 π‘Œ 1 π‘Œ 2 π‘Œ 3 π‘Œ 4 π‘Œ 5 π‘Œ 6 7

  8. Reshaping Tensor into Matrices π‘ˆ = π‘†π‘“π‘‘β„Žπ‘π‘žπ‘“ 𝓀, π’Ÿ : multi-index π’Ÿ mapped into row index, and the remaining indexes into column index Eg. 𝓀 = 𝑄 π‘Œ 1 , π‘Œ 2 , π‘Œ 3 , a 3 rd order tensor and π‘œ = 3 𝑄 2 ;{1,3} = π‘†π‘“π‘‘β„Žπ‘π‘žπ‘“ 𝓀, {2} turns the dimension of π‘Œ 2 into row π‘Œ 3 π‘Œ 1 π‘Œ 1 Slice at dimension of π‘Œ 3 π‘Œ 2 π‘Œ 2 𝓀 π‘Œ 3 = 1 π‘Œ 3 = 2 π‘Œ 3 = 3 π‘Œ 1 π‘ˆ = π‘Œ 2 8

  9. Reshaping 6 th Order Tensor π‘ˆ = 𝑄 1,2,3 ;{4,5,6} = π‘†π‘“π‘‘β„Žπ‘π‘žπ‘“(𝑄 π‘Œ 1 , … , π‘Œ 6 , 1,2,3 ) π‘Œ 6 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 3 3 3 3 3 3 3 3 3 π‘Œ 5 1 1 1 2 2 2 3 3 3 1 1 1 2 2 2 3 3 3 1 1 1 2 2 2 3 3 3 π‘Œ 4 1 2 3 1 2 3 1 2 3 1 2 3 1 2 3 1 2 3 1 2 3 1 2 3 1 2 3 π‘Œ 1 π‘Œ 3 π‘Œ 2 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 3 3 3 3 3 3 3 3 3 1 2 3 1 2 3 1 2 3 1 2 3 1 2 3 1 2 3 1 2 3 1 2 3 1 2 3 1 1 1 2 2 2 3 3 3 1 1 1 2 2 2 3 3 3 1 1 1 2 2 2 3 3 3 Each entry is the probability of a unique assignment to 𝑄(2,3,1,2,1,2) π‘Œ 1 , … , π‘Œ 6 9

  10. Reshaping according to Latent Tree Structure For marginal 𝓠 = 𝑄 π‘Œ 1 , π‘Œ 2 , … , π‘Œ 6 of a latent tree model, reshape it according to the edges in the tree 𝑄 1 ;{2,3,4,5,6} = π‘†π‘“π‘‘β„Žπ‘π‘žπ‘“(𝓠, 1 ) π‘Œ 10 π‘Œ 9 π‘Œ 7 π‘Œ 8 𝑄 1,2 ;{3,4,5,6} = π‘†π‘“π‘‘β„Žπ‘π‘žπ‘“(𝓠, 1,2 ) π‘Œ 1 π‘Œ 2 π‘Œ 3 π‘Œ 4 π‘Œ 5 π‘Œ 6 𝑄 1 ;{2,3,4,5,6} 𝑄 1,2,3,4 ;{5,6} = π‘†π‘“π‘‘β„Žπ‘π‘žπ‘“(𝓠, 1,2,3,4 ) π‘Œ 10 π‘Œ 10 π‘Œ 7 π‘Œ 8 π‘Œ 9 π‘Œ 7 π‘Œ 8 π‘Œ 9 π‘Œ 1 π‘Œ 2 π‘Œ 3 π‘Œ 4 π‘Œ 5 π‘Œ 6 π‘Œ 1 π‘Œ 2 π‘Œ 3 π‘Œ 4 π‘Œ 5 π‘Œ 6 𝑄 1,2 ;{3,4,5,6} 𝑄 1,2,3,4 ;{5,6} 10

  11. Low Rank Structure after Reshaping Size of 𝑄 1,2 ;{3,4,5,6} is π‘œ 2 Γ— π‘œ 4 , but its rank is just π‘œ π‘Œ 10 𝑄 π‘Œ 1 , π‘Œ 2 , … , π‘Œ 6 = π‘Œ 9 π‘Œ 7 π‘Œ 8 𝑄 π‘Œ 1 , π‘Œ 2 𝑦 7 𝑄 𝑦 7 , 𝑦 10 π‘Œ 1 π‘Œ 2 π‘Œ 3 π‘Œ 4 π‘Œ 5 π‘Œ 6 𝑦 7 ,𝑦 10 𝑄(π‘Œ 3 , π‘Œ 4 , π‘Œ 5 , π‘Œ 6 |𝑦 10 ) 𝑄 1,2 ;{3,4,5,6} Use matrix multiplications to express summation over π‘Œ 7 , π‘Œ 10 ⊀ 𝑄 1,2 ;{3,4,5,6} = 𝑄 1,2 | 7 𝑄 7 ;{10} 𝑄 3,4,5,6 |{10} 𝑄 1,2 | 7 ≔ π‘†π‘“π‘‘β„Žπ‘π‘žπ‘“(𝑄 π‘Œ 1 , π‘Œ 2 π‘Œ 7 , 1,2 ) 𝑄 3,4,5,6 | 10 ≔ π‘†π‘“π‘‘β„Žπ‘π‘žπ‘“(𝑄 π‘Œ 3 , π‘Œ 4 , π‘Œ 5 , π‘Œ 6 π‘Œ 10 , 3,4,5,6 ) π‘œ 4 π‘œ 4 π‘œ π‘œ π‘œ π‘œ π‘œ 2 π‘œ 2 = 𝑄 1,2 ;{3,4,5,6} 𝑄 7 ;{10} 11

  12. Low Rank Structure of Latent Tree Model ⊀ 𝑄 3,4 ;{1,2,5,6} = 𝑄 3,4 | 8 𝑄 8 ;{10} 𝑄 1,2,5,6 |{10} π‘œ 4 π‘œ 4 π‘œ π‘œ π‘œ π‘œ π‘œ 2 = π‘œ 2 ⊀ 𝑄 1 ;{2,3,4,5,6} = 𝑄 1 | 7 𝑄 7 ;{7} 𝑄 2,3,4,5,6 |{7} π‘œ 5 = π‘œ π‘œ 5 π‘œ π‘œ π‘œ π‘œ π‘œ π‘Œ 10 π‘Œ 9 π‘Œ 7 π‘Œ 8 All these reshapings are low rank, and with rank π‘œ π‘Œ 1 π‘Œ 2 π‘Œ 3 π‘Œ 4 π‘Œ 5 π‘Œ 6 12

  13. Low Rank Structure of Hidden Markov Models π‘Œ 7 π‘Œ 8 π‘Œ 9 π‘Œ 10 π‘Œ 11 π‘Œ 12 π‘Œ 1 π‘Œ 2 π‘Œ 3 π‘Œ 4 π‘Œ 5 π‘Œ 6 ⊀ 𝑄 1,2 ;{3,4,5,6} = 𝑄 1,2 | 8 𝑄 8 ;{9} 𝑄 3,4,5,6 |{9} π‘œ 4 π‘œ 4 π‘œ π‘œ π‘œ π‘œ π‘œ 2 = π‘œ 2 ⊀ 𝑄 1,2,3 ;{4,5,6} = 𝑄 1,2,3 | 9 𝑄 9 ;{10} 𝑄 4,5,6 |{10} π‘œ 3 π‘œ 3 π‘œ π‘œ π‘œ π‘œ = π‘œ 3 π‘œ 3 13

  14. Key Features of Spectral Algorithms Represent joint probability table of observed variables with low rank factorization, without using the joint table in the computation! Eg. 𝑄 1,…,𝑒 ; 𝑒+1 ,…,2𝑒 = π‘†π‘“π‘‘β„Žπ‘π‘žπ‘“(𝑄 π‘Œ 1 , … , π‘Œ 2𝑒 , 1, … , 𝑒 ) π‘œ 𝑒 β€’ Represent it by low rank factors to avoid exponential blowup β€’ Use clever decomposition π‘œ 𝑒 𝑄 1,…,𝑒 ; 𝑒+1 ,…,2𝑒 technique to avoid directly using all entries from the table β€’ Use singular value decomposition 14

  15. Key Theorem Theorem 1: 𝑄: 𝑑𝑗𝑨𝑓 𝑛 Γ— π‘œ, π‘ π‘π‘œπ‘™ 𝑙 𝐡: 𝑑𝑗𝑨𝑓 π‘œ Γ— 𝑙, π‘ π‘π‘œπ‘™ 𝑙 𝐢: 𝑑𝑗𝑨𝑓 𝑙 Γ— 𝑛, π‘ π‘π‘œπ‘™ 𝑙 𝐢𝑄𝐡 βˆ’1 𝐢𝑄 𝐽𝑔 𝐢𝑄𝐡 π‘—π‘œπ‘€π‘“π‘ π‘’π‘—π‘π‘šπ‘“, π‘’β„Žπ‘“π‘œ 𝑄 = 𝑄𝐡 𝑄 will be the reshaped joint probability table 𝐡 and 𝐢 will be marginalization operator Theorem 1 will be applied recursively Recover several existing spectral algorithms as special cases 15

  16. Marginalization Operator A and B Compute the marginal probability of a subset of variables can be expressed as matrix product 𝑄 π‘Œ 1 , π‘Œ 2 , π‘Œ 3 , π‘Œ 4 = 𝑄 π‘Œ 1 , π‘Œ 2 , π‘Œ 3 , π‘Œ 4 , 𝑦 5 , 𝑦 6 𝑦 5 ,𝑦 6 𝑄 1,2,3 ; 4 = 𝑄 1,2,3 ;{4,5,6} 𝐡 , where 𝐡 = 1 π‘œ βŠ— 1 π‘œ βŠ— 𝐽 π‘œ π‘œ 3 π‘œ π‘œ π‘œ 1 1 π‘œ βŠ— βŠ— π‘œ π‘œ π‘œ 𝐽 π‘œ 3 π‘œ 3 π‘œ 3 = π‘œ 3 = 𝐡 𝐡 1 π‘œ 2 16

  17. Zoom into Marginalization Operation π‘Œ 6 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 3 3 3 3 3 3 3 3 3 π‘Œ 5 1 1 1 2 2 2 3 3 3 1 1 1 2 2 2 3 3 3 1 1 1 2 2 2 3 3 3 π‘Œ 4 1 2 3 1 2 3 1 2 3 1 2 3 1 2 3 1 2 3 1 2 3 1 2 3 1 2 3 = 𝑄 1,2,3 ;{4} 𝑄 1,2,3 ;{4,5,6} 1 3 βŠ— 1 3 βŠ— 𝐽 3 17

  18. Apply Theorem 1 to Latent Tree Model Let π‘Œ 10 𝑄 = 𝑄 1,2 ;{3,4,5,6} π‘Œ 9 𝐡 = 1 π‘œ βŠ— 1 π‘œ βŠ— 1 π‘œ βŠ— 𝐽 π‘œ π‘Œ 7 π‘Œ 8 𝐢 = 𝐽 π‘œ βŠ— 1 π‘œ ⊀ π‘Œ 1 π‘Œ 2 π‘Œ 3 π‘Œ 4 π‘Œ 5 π‘Œ 6 𝑄 1,2 ;{3,4,5,6} Then 𝑄 1,2 ; 3,4,5,6 𝐡 = 𝑄 1,2 ;{3} 𝐢𝑄 1,2 ; 3,4,5,6 = 𝑄 2 ;{3,4,5,6} 𝐢𝑄 1,2 ; 3,4,5,6 𝐡 = 𝑄 2 ;{3} 𝐢𝑄𝐡 βˆ’1 𝐢𝑄 Finally use 𝑄 = 𝑄𝐡 βˆ’1 𝑄 1,2 ;{3,4,5,6} = 𝑄 1,2 ;{3} 𝑄 2 ; 3 𝑄 2 ;{3,4,5,6} 18

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

1 Latent variable models In the next section we will discuss latent variable models for

1 Latent variable models In the next section we will discuss latent variable models for

Statistical Modeling and Analysis of Neural Data (NEU 560) Princeton University, Spring 2018 Jonathan Pillow Lecture 16 notes: Latent variable models and EM Tues, 4.10 1 Latent variable models In the next section we will discuss latent

271 views β€’ 4 slides
Consistent and Efficient Reconstruction of Latent Tree Models Myung Jin Choi Joint work with

Consistent and Efficient Reconstruction of Latent Tree Models Myung Jin Choi Joint work with

Stochastic Systems Group Consistent and Efficient Reconstruction of Latent Tree Models Myung Jin Choi Joint work with Vincent Tan, Anima Anandkumar, and Alan S. Willsky Laboratory for Information and Decision Systems Massachusetts Institute

704 views β€’ 52 slides
What is Latent Tree Analysis (LTA)? Repeated event co-occurrences might Due to common

What is Latent Tree Analysis (LTA)? Repeated event co-occurrences might Due to common

MLA 2017 Latent Tree Analysis Nevin L. Zhang The Hong Kong University of Science and Technology www.cse.ust.hk/~lzhang What is Latent Tree Analysis (LTA)? Repeated event co-occurrences might Due to common hidden causes or genuine direct

813 views β€’ 48 slides
Latent Variable Models CS3750 Xiaoting Li 1 Out utli line Latent Variable Models

Latent Variable Models CS3750 Xiaoting Li 1 Out utli line Latent Variable Models

2/4/2020 Latent Variable Models CS3750 Xiaoting Li 1 Out utli line Latent Variable Models Expectation Maximization Algorithm (EM) Factor Analysis Probabilistic Principal Component Analysis Model Formulation Maximum

654 views β€’ 18 slides
Introduction to Deep Models Part II: Variational Autoencoders and Latent Spaces Nick Winovich

Introduction to Deep Models Part II: Variational Autoencoders and Latent Spaces Nick Winovich

TensorFlow Workshop 2018 Introduction to Deep Models Part II: Variational Autoencoders and Latent Spaces Nick Winovich Department of Mathematics Purdue University July 2018 SIAM@Purdue 2018 - Nick Winovich Introduction to Deep Models : Part

836 views β€’ 25 slides
Language and Document Analysis: Motivating Latent variable Models Wray Buntine National ICT

Language and Document Analysis: Motivating Latent variable Models Wray Buntine National ICT

Language and Document Analysis: Motivating Latent variable Models Wray Buntine National ICT Australia (NICTA) MLSS, ANU, Jan., 2009 Buntine Document Models Part-of-Speech with Hidden Markov Models Topics in Text with Discrete Component

1.25k views β€’ 59 slides
Examples and Implementations [Bayesian approach to Latent Class Models: Definition, Simulation,

Examples and Implementations [Bayesian approach to Latent Class Models: Definition, Simulation,

BIOSTAT 830 GRAPHICAL MODELS Problem Set 4 Case Study: Latent Class Models Note: 1. Due 11:59PM, December 21, 2016. 2. Electronic submission to your instructors email. 3. You are VERY MUCH encouraged to form teams to discuss proofs and

545 views β€’ 3 slides
Learning Overcomplete Latent Variable Models through Tensor Methods Anima Anandkumar UC Irvine

Learning Overcomplete Latent Variable Models through Tensor Methods Anima Anandkumar UC Irvine

Learning Overcomplete Latent Variable Models through Tensor Methods Anima Anandkumar UC Irvine Joint work with Majid Janzamin Rong Ge UC Irvine Microsoft Research Latent Variable Probabilistic Models Latent (hidden) variable h R k ,

769 views β€’ 47 slides
C unobserved construct (e.g. Disordered v. Non- Disordered) Latent classes are mutually

C unobserved construct (e.g. Disordered v. Non- Disordered) Latent classes are mutually

University of Ulster at Magee, Friday 15 th June 2012 Latent Transition Analysis Overview of latent class and Dr Oliver Perra latent transition models Institute of Child Care Research Queens University Belfast email : o.perra@qub.ac.uk

812 views β€’ 38 slides
Chapter 4: Advanced IR Models 4.1 Probabilistic IR 4.2 Statistical Language Models (LMs) 4.3

Chapter 4: Advanced IR Models 4.1 Probabilistic IR 4.2 Statistical Language Models (LMs) 4.3

Chapter 4: Advanced IR Models 4.1 Probabilistic IR 4.2 Statistical Language Models (LMs) 4.3 Latent-Concept Models 4.3.1 Foundations from Linear Algebra 4.3.2 Latent Semantic Indexing (LSI) 4.3.3 Probabilistic Aspect Model (pLSI) 4-1 IRDM

330 views β€’ 32 slides
Learning Latent Variable Models through Tensor Methods Anima Anandkumar U.C. Irvine Challenges

Learning Latent Variable Models through Tensor Methods Anima Anandkumar U.C. Irvine Challenges

Learning Latent Variable Models through Tensor Methods Anima Anandkumar U.C. Irvine Challenges in Unsupervised Learning Learn a latent variable model without labeled examples. E.g. topic models, hidden Markov models, Gaussian mixtures,

763 views β€’ 61 slides
Outline Latent Variable Generative Models Cooperative Vector Quantizer Model Model

Outline Latent Variable Generative Models Cooperative Vector Quantizer Model Model

2/4/2020 CS 3750 Advanced Machine Learning Latent Variable Generative Models II Ahmad Diab AHD23@cs.pitt.edu Feb 4, 2020 Based on slides of Professor Milos Hauskrecht Outline Latent Variable Generative Models Cooperative Vector

435 views β€’ 20 slides
Retrieval by Content Part 3: Text Retrieval Latent Semantic Indexing Srihari: CSE 626 1 Latent

Retrieval by Content Part 3: Text Retrieval Latent Semantic Indexing Srihari: CSE 626 1 Latent

Retrieval by Content Part 3: Text Retrieval Latent Semantic Indexing Srihari: CSE 626 1 Latent Semantic Indexing (LSI) Disadvantage of exclusive use of representing a document as a T-dimensional vector of term weights Users may pose

667 views β€’ 15 slides
Models for Replicated Discrimination Tests: A Synthesis of Latent Class Mixture Models and

Models for Replicated Discrimination Tests: A Synthesis of Latent Class Mixture Models and

Models for Replicated Discrimination Tests Models for Replicated Discrimination Tests: A Synthesis of Latent Class Mixture Models and Generalized Linear Mixed Models Rune Haubo Bojesen Christensen & Per Bruun Brockhoff DTU Informatics

868 views β€’ 21 slides
Case Study: Approximate Bayesian Inference for Latent Gaussian Models by Using Integrated Nested

Case Study: Approximate Bayesian Inference for Latent Gaussian Models by Using Integrated Nested

Case Study: Approximate Bayesian Inference for Latent Gaussian Models by Using Integrated Nested Laplace Approximations BIOSTAT830: Graphical Models December 08, 2016 Introduction - INLA Inference for latent Gaussian Markov random field

605 views β€’ 35 slides
Decision Tree Learning: Part 1 CS 760@UW-Madison Zoo of machine learning models Note: only a

Decision Tree Learning: Part 1 CS 760@UW-Madison Zoo of machine learning models Note: only a

Decision Tree Learning: Part 1 CS 760@UW-Madison Zoo of machine learning models Note: only a subset of ML methods Figure from scikit-learn.org Even a subarea has its own collection Figure from asimovinstitute.org The lectures organized

534 views β€’ 34 slides
19: Game Proofs & Separations 15-424: Foundations of Cyber-Physical Systems Andr e Platzer

19: Game Proofs & Separations 15-424: Foundations of Cyber-Physical Systems Andr e Platzer

19: Game Proofs & Separations 15-424: Foundations of Cyber-Physical Systems Andr e Platzer aplatzer@cs.cmu.edu Computer Science Department Carnegie Mellon University, Pittsburgh, PA 0.5 0.4 0.3 0.2 1.0 0.1 0.8 0.6 0.4 0.2

893 views β€’ 78 slides
Recursively defined trees and their maximal order types Jeroen Van der Meeren 2 CTFM 2013 2 Work

Recursively defined trees and their maximal order types Jeroen Van der Meeren 2 CTFM 2013 2 Work

Recursively defined trees and their maximal order types Jeroen Van der Meeren 2 CTFM 2013 2 Work related with a program between Michael Rathjen and Andreas Weiermann Introduction Recursively defined trees Conclusions Structure presentation 1

435 views β€’ 39 slides
Verification of Concurrent Systems Ahmed Bouajjani LIAFA, University Paris Diderot Paris 7

Verification of Concurrent Systems Ahmed Bouajjani LIAFA, University Paris Diderot Paris 7

Verification of Concurrent Systems Ahmed Bouajjani LIAFA, University Paris Diderot Paris 7 MOVEP12, CIRM, December 2012 A. Bouajjani (LIAFA, UP7) Verification of Concurrent Systems December 2012 1 / 42 Concurrent Programs Parallel

1.26k views β€’ 112 slides
Big and Small Steps for Fast and Slow Provability Paula Henk illc , University of Amsterdam

Big and Small Steps for Fast and Slow Provability Paula Henk illc , University of Amsterdam

GL GLT Fast provability Slow provability Big and Small Steps for Fast and Slow Provability Paula Henk illc , University of Amsterdam September 1, 2016 1 / 6 GL GLT Fast provability Slow provability G odel-L ob provability logic GL

334 views β€’ 5 slides
A Non-wellfounded, Labelled Proof System for Propositional Dynamic Logic Simon Docherty,

A Non-wellfounded, Labelled Proof System for Propositional Dynamic Logic Simon Docherty,

A Non-wellfounded, Labelled Proof System for Propositional Dynamic Logic Simon Docherty, University College London Reuben N. S. Rowe, Royal Holloway University of London TABLEAUX 2019 2 nd 5 th September 2019, Middlesex University, London, UK

427 views β€’ 40 slides
NP Reasoning in the Monotone -Calculus (IJCAR 2020) Daniel Hausmann and Lutz Schr oder

NP Reasoning in the Monotone -Calculus (IJCAR 2020) Daniel Hausmann and Lutz Schr oder

NP Reasoning in the Monotone -Calculus (IJCAR 2020) Daniel Hausmann and Lutz Schr oder University Erlangen-Nuremberg, Germany Highlights 2020 16 September 2020 0 / 5 Satisfiability Checking Complexities of satisfiability checking for

162 views β€’ 12 slides
Table of contents 1. Quantum gravity & BH thermodynamics 2. AdS / CFT correspondence 3.

Table of contents 1. Quantum gravity & BH thermodynamics 2. AdS / CFT correspondence 3.

Statistical black hole entropy and AdS 2 / CFT 1 Asymptotic symmetries and dual boundary theory Matteo Ciulu 17.5.2017 Universit a degli studi di Cagliari Table of contents 1. Quantum gravity & BH thermodynamics 2. AdS / CFT

762 views β€’ 25 slides
Characterising State Spaces of Concurrent Systems Eike Best University of Oldenburg Work

Characterising State Spaces of Concurrent Systems Eike Best University of Oldenburg Work

Characterising State Spaces of Concurrent Systems Eike Best University of Oldenburg Work started with Philippe Darondeau and continued with Raymond Devillers Open Problems in Concurrency Theory Bertinoro, June 18, 2014 System analysis vs.

719 views β€’ 24 slides

More recommend