Rafael Izbicki | PhD
Rafael Izbicki | PhD
Home
Featured Publications
Lecture Notes
Teaching
Talks
Posts
Students
Contact
Light
Dark
Automatic
1
Diagnostics for Conditional Density Models and Bayesian Inference Algorithms
D. Zhao
,
N. Dalmasso
,
Rafael Izbicki
,
A. B. Lee
September, 2021
Proceedings of Machine Learning Research (UAI Track)
paper
PDF
Identifying Distributional Differences in Convective Evolution Prior to Rapid Intensification in Tropical Cyclones
Tropical cyclone (TC) intensity forecasts are issued by human forecasters who evaluate spatio-temporal observations (e.g., satellite …
T. McNeely
,
G. Vincent
,
Rafael Izbicki
,
K. M. Wood
,
A. B. Lee
February, 2021
Tackling Climate Change with Machine Learning workshop at NeurIPS 2021 (poster)
PDF
Flexible distribution-free conditional predictive bands using density estimators
Conformal methods create prediction bands that control average coverage assuming solely i.i.d. data. Besides average coverage, one …
Gilson Shimizu
,
Rafael Izbicki
,
Rafael B. Stern
April, 2020
In
PMLR
PDF
Cite
Source Document
Confidence Sets and Hypothesis Testing in a Likelihood-Free Inference Setting
Parameter estimation, statistical tests and confidence sets are the cornerstones of classical statistics that allow scientists to make inferences about the underlying process that generated the observed data. A key question is whether one can still construct hypothesis tests and confidence sets with proper coverage and high power in a so-called likelihood-free inference (LFI) setting; that is, a setting where the likelihood is not explicitly known but one can forward-simulate observable data according to a stochastic model. We present ACORE, a frequentist approach to LFI that first formulates the classical likelihood ratio test (LRT) as a parametrized classification problem, and then uses the equivalence of tests and confidence sets to build confidence regions for parameters of interest. We also present a goodness-of-fit procedure for checking whether the constructed tests and confidence regions are valid.
Niccolò Dalmasso
,
Rafael Izbicki
,
Ann B. Lee
February, 2020
Proceedings of Machine Learning Research (ICML Track)
Preprint
PDF
Validation of Approximate Likelihood and Emulator Models for Computationally Intensive Simulations
Complex phenomena in engineering and the sciences are often modeled with computationally intensive feed-forward simulations for which a …
N. Dalmasso
,
A. B. Lee
,
Rafael Izbicki
,
T. Pospisil
,
I. Kim
,
C. Lin
January, 2020
Proceedings of Machine Learning Research (AISTATS Track)
Preprint
PDF
ABC-CDE: Toward Approximate Bayesian Computation with Complex High-Dimensional Data and Limited Simulations
We show how a nonparametric conditional density estimation (CDE) framework helps address three nontrivial challenges in ABC. (i) how to efficiently estimate the posterior distribution with limited simulations and different types of data, (ii) how to tune and compare the performance of ABC and related methods in estimating the posterior itself, rather than just certain properties of the density, and (iii) how to efficiently choose among a large set of summary statistics based on a CDE surrogate loss.
Rafael Izbicki
,
Taylor Pospisil
,
Ann B. Lee
February, 2019
Journal of Computational and Graphical Statistics
Preprint
PDF
Conditional density estimation using Fourier series and neural networks
Most machine learning tools aim at creating good predictions for new samples. However, obtaining 100% is not feasible in most problems, …
M. H. de A. Inácio
,
Rafael Izbicki
May, 2018
KDMiLe - Symposium on Knowledge Discovery, Mining and Learning - Algorithms Track
PDF
Converting High-Dimensional Regression to High-Dimensional Conditional Density Estimation
Here we propose a fully nonparametric approach to conditional density estimation that reformulates CDE as a non-parametric orthogonal series problem where the expansion coefficients are estimated by regression. By taking such an approach, one can efficiently estimate conditional densities and not just expectations in high dimensions by drawing upon the success in high-dimensional regression. We show applications to photometric galaxy data, Twitter data, and line-of-sight velocities in a galaxy cluster.
Rafael Izbicki
,
Ann B. Lee
November, 2017
Electronic Journal of Statistics
Preprint
PDF
Code
Prior Shift Using the Ratio Estimator
Several machine learning applications use classifiers as a way of quantifying the prevalence of positive class labels in a target …
Afonso F. Vaz
,
Rafael Izbicki
,
Rafael B. Stern
May, 2017
In
37th MaxEnt
PDF
Cite
Photo-z estimation: An example of nonparametric conditional density estimation under selection bias
We describe a general framework for properly constructing and assessing nonparametric conditional density estimators under selection bias, and for combining two or more estimators for optimal performance. This leads to new improved photo-z estimators. We illustrate our methods on data from the Sloan Data Sky Survey and an application to galaxy-galaxy lensing.
Rafael Izbicki
,
Ann B. Lee
,
Peter E. Freeman
February, 2017
The Annals of Applied Statistics
Preprint
PDF
»
Cite
×