diverse particle selection for high dimensional inference
play

Diverse Particle Selection for High-Dimensional Inference in - PowerPoint PPT Presentation

Dec 03, 2023 •127 likes •830 views

Diverse Particle Selection for High-Dimensional Inference in Graphical Models Erik Sudderth UC Irvine Computer Science Collaborators: Particle Max-Product: Jason Pacheco, MIT Human Pose: Silvia Zuffi & Michael Black, MPI Tubingen

  1. Diverse Particle Selection for High-Dimensional Inference in Graphical Models Erik Sudderth UC Irvine Computer Science Collaborators: Ø Particle Max-Product: Jason Pacheco, MIT Ø Human Pose: Silvia Zuffi & Michael Black, MPI Tubingen Related papers at ICML 2014 & ICML 2015

  2. High-Dimensional Inference Data Unknowns Estimate Probability Model Discrete Efficient inference based on Unknowns combinatorial optimization Unless we make unrealistic model Continuous approximations, no efficient general Unknowns solutions. Standard gradient-based optimization is ineffective.

  3. Continuous Inference Problems Human pose estimation & tracking Protein structure & side chain prediction Robot motion & vehicle path planning

  4. Maximum a Posteriori (MAP) Data Unknowns Posterior MAP Estimate * Posterior often intractable and multimodal complicating exact MAP inference:

  5. Maximum a Posteriori (MAP) Data Unknowns Posterior Local Optimum * * Posterior often intractable and multimodal complicating exact MAP inference: Local optima can be useful when models are inaccurate or data are noisy.

  6. Goal Develop maximum a posteriori (MAP) inference algorithms for continuous probability models that: Ø Apply to any pairwise graphical model, even if model is complex (highly non-Gaussian) Ø Are black-box (no gradients required) Ø Will reliably infer multiple local optima

  7. Pairwise Graphical Models x s ∈ R d Ø Nodes are continuous random variables Ø Potentials encode statistical relationships Ø Edges indicate direct, pairwise energetic interactions x 1 x 4 x 2 x 8 x 3 x 9 x 7 x 5 x 6

  8. Message Passing on Trees Global MAP inference decomposes into local computations via graph structure…

  9. Max-Product Belief Propagation Max-Product Belief Propagation Finding max-marginals via message-passing Y q s ( x s ) = max x t 6 = s p ( x s , x t 6 = s ) ∝ ψ s ( x s ) m ts ( x s ) t 2 Γ ( s ) Why max-marginals? Ø Directly encode global MAP Ø Other modes important: models approximate, data uncertain Max-product dynamic programming finds exact max-marginals on tree-structured graphs.

  10. Articulated Pose Estimation [ Zuffi et al., CVPR 2012 ] Complicated Non-Gaussian Likelihood Compatibility Deformable Structures (DS): Continuous state for part shape , location , orientation, scale . PCA Shape

Recommend

High Dimensional Predictive Inference Workshop on Current Trends and Challenges in Model

High Dimensional Predictive Inference Workshop on Current Trends and Challenges in Model

High Dimensional Predictive Inference Workshop on Current Trends and Challenges in Model Selection and Related Areas Vienna, Austria July 2008 Ed George The Wharton School (joint work with L. Brown, F. Liang, and X. Xu) 1. Estimating a

849 views • 27 slides
Random projections, reweighting and half-sampling for high-dimensional statistical inference Art

Random projections, reweighting and half-sampling for high-dimensional statistical inference Art

MC for high-dimensional statistics 1 Random projections, reweighting and half-sampling for high-dimensional statistical inference Art B. Owen Stanford University based on joint works with: Dean Eckles Facebook Inc. Sarah Emerson Oregon

603 views • 56 slides
Inference for parameters of interest after lasso model selection David M. Drukker Executive

Inference for parameters of interest after lasso model selection David M. Drukker Executive

Inference for parameters of interest after lasso model selection David M. Drukker Executive Director of Econometrics Stata Canadian Stata Users Group meeting 25 May 2019 High-dimensional models include too many potential covariates for a

573 views • 36 slides
Using the lasso in Stata for inference in high-dimensional models David M. Drukker Executive

Using the lasso in Stata for inference in high-dimensional models David M. Drukker Executive

Using the lasso in Stata for inference in high-dimensional models David M. Drukker Executive Director of Econometrics Stata Spanish Stata User Group Meeting 17 Octubre 2019 Outline What are high-dimensional models? 1 What is the lasso? 2

1.04k views • 49 slides
Selective Inference via the Condition on Selection Framework: Inference after Variable Selection

Selective Inference via the Condition on Selection Framework: Inference after Variable Selection

Selective Inference via the Condition on Selection Framework: Inference after Variable Selection Jason D. Lee Stanford University Collaborators: Yuekai Sun, Dennis Sun, Qiang Liu, and Jonathan Taylor. Slides at

538 views • 49 slides
Dimension Reduction and High-Dimensional Data Estimation and Inference with Application to

Dimension Reduction and High-Dimensional Data Estimation and Inference with Application to

Dimension Reduction and High-Dimensional Data Estimation and Inference with Application to Genomics and Neuroimaging Maxime Turgeon April 9, 2019 McGill University Department of Epidemiology, Biostatistics, and Occupational Health 1/21

430 views • 26 slides
High Dimensional M -Estimation & Inference from Observational Data with Incomplete Responses

High Dimensional M -Estimation & Inference from Observational Data with Incomplete Responses

High Dimensional M -Estimation & Inference from Observational Data with Incomplete Responses A Semi-Parametric Doubly Robust Framework Abhishek Chakrabortty 1 Department of Statistics University of Pennsylvania Group Meeting April 24, 2019

1.57k views • 140 slides
Using the lasso in Stata for inference in high-dimensional models David M. Drukker Executive

Using the lasso in Stata for inference in high-dimensional models David M. Drukker Executive

Using the lasso in Stata for inference in high-dimensional models David M. Drukker Executive Director of Econometrics Stata London Stata Conference 5-6 September 2019 Outline What are high-dimensional models? 1 What is the lasso? 2 Using

895 views • 41 slides
High-dimensional causal inference, graphical modeling and structural equation models Peter B

High-dimensional causal inference, graphical modeling and structural equation models Peter B

High-dimensional causal inference, graphical modeling and structural equation models Peter B uhlmann Seminar f ur Statistik, ETH Z urich cannot do confirmatory causal inference without randomized intervention experiments... but we can

1.03k views • 88 slides
Joint variable and rank selection for parsimonious estimation of high dimensional matrices

Joint variable and rank selection for parsimonious estimation of high dimensional matrices

Framework and motivation Joint Rank and Row Selection Methods Two-step JRRS estimators Numerical performance and examples Summary Joint variable and rank selection for parsimonious estimation of high dimensional matrices Florentina Bunea

370 views • 26 slides
LR-GLM: High-Dimensional Bayesian Inference Using Low-Rank Data Approximations Brian Trippe ,

LR-GLM: High-Dimensional Bayesian Inference Using Low-Rank Data Approximations Brian Trippe ,

LR-GLM: High-Dimensional Bayesian Inference Using Low-Rank Data Approximations Brian Trippe , Jonathan Huggins, Raj Agrawal, and Tamara Broderick LR-GLM: High-Dimensional Bayesian Inference Using Low-Rank Data Approximations Brian Trippe ,

502 views • 23 slides
Bilinear generalized approximate message passing (BiG-AMP) for High Dimensional Inference Phil

Bilinear generalized approximate message passing (BiG-AMP) for High Dimensional Inference Phil

Bilinear generalized approximate message passing (BiG-AMP) for High Dimensional Inference Phil Schniter Collaborators: Jason Parker @OSU, Jeremy Vila @OSU, and Volkan Cehver @EPFL With support from NSF CCF-1218754, NSF CCF-1018368, NSF

686 views • 31 slides
Variable selection and parameter tuning in high-dimensional prediction Christoph Bernau and

Variable selection and parameter tuning in high-dimensional prediction Christoph Bernau and

Setup Results Discussion Variable selection and parameter tuning in high-dimensional prediction Christoph Bernau and Anne-Laure Boulesteix Institut f ur Medizinische Informationsverarbeitung, Biometrie und Epidemiologie

186 views • 14 slides
Principal Component of Explained Variance High-Dimensional Estimation and Inference Max Turgeon

Principal Component of Explained Variance High-Dimensional Estimation and Inference Max Turgeon

Principal Component of Explained Variance High-Dimensional Estimation and Inference Max Turgeon February 14th, 2020 University of Manitoba Departments of Statistics and Computer Science 1/47 Introduction In modern statistics, we often

844 views • 55 slides
RECURRENT KALMAN NETWORKS Factorized Inference in High-Dimensional Deep Feature Spaces Philipp

RECURRENT KALMAN NETWORKS Factorized Inference in High-Dimensional Deep Feature Spaces Philipp

RECURRENT KALMAN NETWORKS Factorized Inference in High-Dimensional Deep Feature Spaces Philipp Becker 1 2 3 Harit Pandya 4 Gregor Gebhardt 1 Chen Zhao 5 James Taylor 6 Gerhard Neumann 4 2 3 1: Computational Learning for Autonomous Systems, TU

506 views • 13 slides
Free energy of a particle in high-dimensional Gaussian potentials with isotropic increments Anton

Free energy of a particle in high-dimensional Gaussian potentials with isotropic increments Anton

Free energy of a particle in high-dimensional Gaussian potentials with isotropic increments Anton Klimovsky EURANDOM Eindhoven University of Technology September 1, 2011, Prague http://arxiv.org/abs/1108.5300 Gaussian fields with isotropic

379 views • 17 slides
High-dimensional graphical model selection: Practical and information-theoretic limits Martin

High-dimensional graphical model selection: Practical and information-theoretic limits Martin

High-dimensional graphical model selection: Practical and information-theoretic limits Martin Wainwright Departments of Statistics, and EECS UC Berkeley, California, USA Based on joint work with: John Lafferty (CMU), Pradeep Ravikumar (UC

338 views • 22 slides
Methods for Robust High Dimensional Graphical Model Selection Bala Rajaratnam Department of

Methods for Robust High Dimensional Graphical Model Selection Bala Rajaratnam Department of

Methods for Robust High Dimensional Graphical Model Selection Bala Rajaratnam Department of Statistics Stanford University Fields Institute Joint work with S. Oh (UC Berkeley) and K. Khare (U. Florida) Motivation Availability of

1.09k views • 58 slides
Feature Selection and Classification Pairwise Combinations for High-dimensional Tumour Biomedical

Feature Selection and Classification Pairwise Combinations for High-dimensional Tumour Biomedical

Feature Selection and Classification Pairwise Combinations for High-dimensional Tumour Biomedical Datasets A. Dziomdziora A. Wosiak Lodz University of Technology Institute of Information Technology Theoretical Foundations of Machine Learning,

625 views • 33 slides
Particle Filtering Sometimes |X| is too big to use exact inference |X| may be too big to

Particle Filtering Sometimes |X| is too big to use exact inference |X| may be too big to

Particle Filtering Sometimes |X| is too big to use exact inference |X| may be too big to even store B(X) E.g. X is continuous |X| 2 may be too big to do updates Solution: approximate inference Track samples of X, not

284 views • 27 slides
Signal Rate Inference for Dimensional Faust Multi-Dimensional Faust Y. Orlarey P. Jouvelot

Signal Rate Inference for Dimensional Faust Multi-Dimensional Faust Y. Orlarey P. Jouvelot

Signal Rate Inference for Multi- Signal Rate Inference for Dimensional Faust Multi-Dimensional Faust Y. Orlarey P. Jouvelot Signals Yann Orlarey 1 Pierre Jouvelot 2 Types/rates Inference 1 Grame, France Correctness Algorithm 2 MINES

525 views • 15 slides
Towards robust feature selection for high-dimensional, small sample settings Yvan Saeys

Towards robust feature selection for high-dimensional, small sample settings Yvan Saeys

Towards robust feature selection for high-dimensional, small sample settings Yvan Saeys Bioinformatics and Evolutionary Genomics, Ghent University, Belgium yvan.saeys@psb.ugent.be Marseille, January 14th, 2010 Background: biomarker discovery

1.16k views • 52 slides
The Factor-Lasso and K-Step Bootstrap Approach for Inference in High-Dimensional Economic

The Factor-Lasso and K-Step Bootstrap Approach for Inference in High-Dimensional Economic

The Factor-Lasso and K-Step Bootstrap Approach for Inference in High-Dimensional Economic Applications Christian Hansen Yuan Liao May 2017 Montreal Hansen and Liao Factor-Lasso Introduction Observe many control variables Two popular

471 views • 26 slides
Bayesian Causal Inference in High Dimensional Data Settings Jacob Spertus and Sharon-Lise Normand

Bayesian Causal Inference in High Dimensional Data Settings Jacob Spertus and Sharon-Lise Normand

Bayesian Causal Inference in High Dimensional Data Settings Jacob Spertus and Sharon-Lise Normand Harvard Medical School & School of Public Health Funded by R01-GM111339 and U01-FDA004493 Thanks to Organizer: Mariel Finucane , Mathematica

187 views • 14 slides

More recommend