# Statistical Theory and Methods for Complex, High-Dimensional Data

Created: | 2008-02-01 14:48 |
---|---|

Institution: | Isaac Newton Institute for Mathematical Sciences |

Description: | Most of twentieth-century statistical theory was restricted to problems in which the number p of 'unknowns', such as parameters, is much less than n, the number of experimental units. However, the practical environment has changed dramatically over the last twenty years or so, with the spectacular evolution of computing facilities and the emergence of applications in which the number of experimental units is comparatively small but the underlying dimension is massive, leading to the desire to fit complex models for which the effective p is very large. Areas of application include image analysis, microarray analysis, finance, document classification, astronomy and atmospheric science. Some methodological advances have been made, but there is a need to provide firm consolidation in the form of a systematic and critical assessment of the new approaches as well as appropriate theoretical underpinning in this 'large p, small n' context. The existence of key applications strongly motivates the programme, but the fundamental aim is to promote core theoretical and methodological research. Both frequentist and Bayesian paradigms will be featured. The programme is directed at a broad research community, including both mainstream statisticians and the growing population of researchers in machine learning. The methodological issues likely to be covered fall roughly into four overlapping categories:
* strategies for explicit and implicit dimension-reduction, including latent-structure methods, semiparametric models and large-scale multiple testing; * classification methods for complex datasets, including machine-learning methods such as support vector machines; * asymptotics for increasing dimension, including the application of random matrix theory to high-dimensional multivariate methods; * graphical and other visualisation methods for complex datasets. EVENTS: - Contemporary Frontiers in High-Dimensional Statistical Data Analysis http://www.newton.ac.uk/programmes/SCH/schw01.html - High Dimensional Statistics in Biology http://www.newton.ac.uk/programmes/SCH/schw02.html - Inference and Estimation in Probabilistic Time-Series Models http://www.newton.ac.uk/programmes/SCH/schw05.html - Future Directions in High-Dimensional Data Analysis http://www.newton.ac.uk/programmes/SCH/schw03.html |

# Media items

This collection contains 129 media items.

### Media items

#### A Bayesian method for non-Gaussian autoregressive quantile function time series models

Cai, Y (Plymouth)

Wednesday 18 June 2008, 15:30-16:10

Inference and Estimation in Probabilistic Time-Series Models

**Collection**:
Statistical Theory and Methods for Complex, High-Dimensional Data

**Institution**:
Isaac Newton Institute for Mathematical Sciences

**Created**:
Tue 24 Jun 2008

#### A Bayesian probabilistic approach to transform public microarray repositories into disease diagnosis databases

Huang, H (UC Berkeley)

Friday 04 April 2008, 14:00-15:00

High Dimensional Statistics in Biology

**Collection**:
Statistical Theory and Methods for Complex, High-Dimensional Data

**Institution**:
Isaac Newton Institute for Mathematical Sciences

**Created**:
Fri 11 Apr 2008

#### A database of foreign exchange deals

Clarkson, P (BNP Paribas)

Thursday 31 January 2008, 11:00-12:00

**Collection**:
Statistical Theory and Methods for Complex, High-Dimensional Data

**Institution**:
Isaac Newton Institute for Mathematical Sciences

**Created**:
Sun 3 Feb 2008

#### A geometric perspective on learning theory and algorithms

Niyogi, P (Chicago)

Thursday 10 January 2008, 16:30-17:30

Contemporary Frontiers in High-Dimensional Statistical Data Analysis

**Collection**:
Statistical Theory and Methods for Complex, High-Dimensional Data

**Institution**:
Isaac Newton Institute for Mathematical Sciences

**Created**:
Tue 22 Jan 2008

#### A methodological framework for Monte Carlo estimation of continuous-time processes

Papaspiliopoulos, O (Universitat Pompeu Fabra)

Friday 20 June 2008, 14:00-15:00

Inference and Estimation in Probabilistic Time-Series Models

**Collection**:
Statistical Theory and Methods for Complex, High-Dimensional Data

**Institution**:
Isaac Newton Institute for Mathematical Sciences

**Created**:
Fri 27 Jun 2008

#### A modern perspective on auxiliary particle filters

Whiteley, N (Cambridge)

Wednesday 18 June 2008, 16:50-17:30

Inference and Estimation in Probabilistic Time-Series Models

**Collection**:
Statistical Theory and Methods for Complex, High-Dimensional Data

**Institution**:
Isaac Newton Institute for Mathematical Sciences

**Created**:
Tue 24 Jun 2008

#### A physicist's approach to high-dimensional inference

Hoyle, D (Manchester)

Friday 11 January 2008, 14:00-15:00

Contemporary Frontiers in High-Dimensional Statistical Data Analysis

**Collection**:
Statistical Theory and Methods for Complex, High-Dimensional Data

**Institution**:
Isaac Newton Institute for Mathematical Sciences

**Created**:
Wed 23 Jan 2008

#### Adaptive Monte Carlo Markov Chains

Moulines, E (CNRS)

Friday 20 June 2008, 11:30-12:30

Inference and Estimation in Probabilistic Time-Series Models

**Collection**:
Statistical Theory and Methods for Complex, High-Dimensional Data

**Institution**:
Isaac Newton Institute for Mathematical Sciences

**Created**:
Fri 27 Jun 2008

#### Analysis of graphs using diffusion processes and random walks (a random walk through spectral graph theory)

Hancock, E (York)

Tuesday 18 March 2008, 11:00-12:00

**Collection**:
Statistical Theory and Methods for Complex, High-Dimensional Data

**Institution**:
Isaac Newton Institute for Mathematical Sciences

**Created**:
Wed 26 Mar 2008

#### Applications of approximate inference and experimental design for sparse (generalised) linear models

Seeger, MW (MPI for Biological Cybernetics)

Friday 27 June 2008, 11:30-12:30

Future Directions in High-Dimensional Data Analysis

**Collection**:
Statistical Theory and Methods for Complex, High-Dimensional Data

**Institution**:
Isaac Newton Institute for Mathematical Sciences

**Created**:
Tue 15 Jul 2008

#### Approximate genealogical inference

McVean, G (Oxford)

Friday 04 April 2008, 10:00-11:00

High Dimensional Statistics in Biology

**Collection**:
Statistical Theory and Methods for Complex, High-Dimensional Data

**Institution**:
Isaac Newton Institute for Mathematical Sciences

**Created**:
Tue 15 Apr 2008

#### Approximate Inference for Continuous Time Markov Processes

Opper, M (Technische Universität Berlin)

Thursday 19 June 2008, 11:30-12:30

Inference and Estimation in Probabilistic Time-Series Models

**Collection**:
Statistical Theory and Methods for Complex, High-Dimensional Data

**Institution**:
Isaac Newton Institute for Mathematical Sciences

**Created**:
Wed 25 Jun 2008

#### Approximation of functional spatial regression models using bivariate splines

Guillas, S (University College London)

Thursday 05 June 2008, 11:00-12:00

**Collection**:
Statistical Theory and Methods for Complex, High-Dimensional Data

**Institution**:
Isaac Newton Institute for Mathematical Sciences

**Created**:
Tue 17 Jun 2008

#### Assessing high-dimensional latent variable models

Murray, I (Toronto)

Thursday 15 May 2008, 11:00-12:00

**Collection**:
Statistical Theory and Methods for Complex, High-Dimensional Data

**Institution**:
Isaac Newton Institute for Mathematical Sciences

**Created**:
Wed 28 May 2008

#### Bayesian Gaussian process models for multi-sensor time-series prediction

Roberts, S (Oxford)

Thursday 19 June 2008, 17:00-17:30

Inference and Estimation in Probabilistic Time-Series Models

**Collection**:
Statistical Theory and Methods for Complex, High-Dimensional Data

**Institution**:
Isaac Newton Institute for Mathematical Sciences

**Created**:
Thu 26 Jun 2008

#### Bayesian hierarchical clustering

Heller, K (UCL)

Monday 18 February 2008, 15:00-15:30

**Collection**:
Statistical Theory and Methods for Complex, High-Dimensional Data

**Institution**:
Isaac Newton Institute for Mathematical Sciences

**Created**:
Thu 21 Feb 2008

#### Bayesian nonparametric latent feature models

Ghahramani, Z (Cambridge)

Monday 18 February 2008, 15:30-16:00

**Collection**:
Statistical Theory and Methods for Complex, High-Dimensional Data

**Institution**:
Isaac Newton Institute for Mathematical Sciences

**Created**:
Thu 21 Feb 2008

#### Bootstrap and parametric inference: successes and challenges

Young, A (Imperial)

Monday 07 January 2008, 15:30-16:30

Contemporary Frontiers in High-Dimensional Statistical Data Analysis

**Collection**:
Statistical Theory and Methods for Complex, High-Dimensional Data

**Institution**:
Isaac Newton Institute for Mathematical Sciences

**Created**:
Thu 17 Jan 2008

#### Breakdown point of model selection when the number of variables exceeds the number of observations

Donoho, D (Stanford)

Monday 07 January 2008, 10:00-11:00

Contemporary Frontiers in High-Dimensional Statistical Data Analysis

**Collection**:
Statistical Theory and Methods for Complex, High-Dimensional Data

**Institution**:
Isaac Newton Institute for Mathematical Sciences

**Created**:
Wed 16 Jan 2008

#### Challenge of dimensionality in model selection and classification

Fan, J (Princeton)

Tuesday 08 January 2008, 15:30-16:30

Contemporary Frontiers in High-Dimensional Statistical Data Analysis

**Collection**:
Statistical Theory and Methods for Complex, High-Dimensional Data

**Institution**:
Isaac Newton Institute for Mathematical Sciences

**Created**:
Fri 18 Jan 2008