• Corpus ID: 220425142

Double spike Dirichlet priors for structured weighting.

@article{Lin2020DoubleSD,
  title={Double spike Dirichlet priors for structured weighting.},
  author={Huiming Lin and Meng Li},
  journal={arXiv: Methodology},
  year={2020}
}
Assigning weights to a large pool of objects is a fundamental task in a wide variety of applications. In this article, we introduce a concept of structured high-dimensional probability simplexes, whose most components are zero or near zero and the remaining ones are close to each other. Such structure is well motivated by 1) high-dimensional weights that are common in modern applications, and 2) ubiquitous examples in which equal weights---despite their simplicity---often achieve favorable or… 

Figures from this paper

References

SHOWING 1-10 OF 49 REFERENCES

Gibbs posterior for variable selection in high-dimensional classification and data mining

TLDR
A completely new direction will be considered here to study BVS with a Gibbs posterior originating in statistical mechanics, and a convenient Markov chain Monte Carlo algorithm is developed to implement B VS with the Gibbs posterior.

Methods for Sparse and Low-Rank Recovery under Simplex Constraints

TLDR
It is argued that ERM combined with a subsequent sparsification step like thresholding is superior to the heuristic of using $\ell_1$-regularization after dropping the sum constraint and subsequent normalization, and it is shown that any sparsity-promoting regularizer under simplex constraints cannot be convex.

Minimax Optimal Bayesian Aggregation

TLDR
This paper proposes Bayesian convex and linear aggregation approaches motivated by regression applications and shows that the proposed approach is minimax optimal when the true data-generating model is a convex or linear combination of models in the list.

SLOPE-ADAPTIVE VARIABLE SELECTION VIA CONVEX OPTIMIZATION.

TLDR
SLOPE, short for Sorted L-One Penalized Estimation, is the solution to λBH and appears to have appreciable inferential properties under more general designs X while having substantial power, as demonstrated in a series of experiments running on both simulated and real data.

BAYESIAN LINEAR REGRESSION WITH SPARSE PRIORS

TLDR
Under compatibility conditions on the design matrix, the posterior distribution is shown to contract at the optimal rate for recovery of the unknown sparse vector, and to give optimal prediction of the response vector.

Machine Learning for Regularized Survey Forecast Combination: Partially-Egalitarian Lasso and its Derivatives

TLDR
Direct subset-averaging procedures motivated by the structure of partially-egalitarian LASSO and the lessons learned are proposed and explored, which outperform simple average and median forecasts and perform approximately as well as the ex-post best forecaster.

Super Learner

TLDR
A fast algorithm for constructing a super learner in prediction which uses V-fold cross-validation to select weights to combine an initial set of candidate learners.

Classification and Regression by randomForest

TLDR
random forests are proposed, which add an additional layer of randomness to bagging and are robust against overfitting, and the randomForest package provides an R interface to the Fortran programs by Breiman and Cutler.

Aggregation for Gaussian regression

This paper studies statistical aggregation procedures in the regression setting. A motivating factor is the existence of many different methods of estimation, leading to possibly competing

Machine Learning Benchmarks and Random Forest Regression

Breiman (2001a,b) has recently developed an ensemble classification and regression approach that displayed outstanding performance with regard prediction error on a suite of benchmark datasets. As