Search Results for author:
Found 11 papers, 2 papers with code
Effect of Weight Quantization on Learning Models by Typical Case Analysis
However, the selection of quantization hyperparameters, like the number of bits and value range for weight quantization, remains an underexplored area.
Evolutionary Shaping of Low-Dimensional Path Facilitates Robust and Plastic Switching Between Phenotypes
The fitness for selection is given so that it takes a higher value as more of the active sites take two requested spin configurations depending on the regulation.
Prediction Errors for Penalized Regressions based on Generalized Approximate Message Passing
We discuss the prediction accuracy of assumed statistical models in terms of prediction errors for the generalized linear model and penalized maximum likelihood methods.
Active pooling design in group testing based on Bayesian posterior prediction
In identifying infected patients in a population, group testing is an effective method to reduce the number of tests and correct the test errors.
Bayesian inference of infected patients in group testing with prevalence estimation
For the case in which the test returns a false result with finite probability, we propose Bayesian inference and a corresponding belief propagation (BP) algorithm to identify the infected patients from the results of tests performed on the pool.
Cross validation in sparse linear regression with piecewise continuous nonconvex penalties and its acceleration
Second, we develop an approximate formula efficiently computing the cross-validation error without actually conducting the cross-validation, which is also applicable to the non-i. i. d.
Perfect reconstruction of sparse signals with piecewise continuous nonconvex penalties and nonconvexity control
A part of the discrepancy is resolved by introducing the control of the nonconvexity parameters to guide the AMP trajectory to the basin of the attraction.
Estimator of Prediction Error Based on Approximate Message Passing for Penalized Linear Regression
We propose an estimator of prediction error using an approximate message passing (AMP) algorithm that can be applied to a broad range of sparse penalties.
Approximate message passing for nonconvex sparse regularization with stability and asymptotic analysis
Through asymptotic analysis, we show the correspondence between the density evolution of SCAD-AMP and the replica symmetric solution.
Phase transitions and sample complexity in Bayes-optimal matrix factorization
We use the tools of statistical mechanics - the cavity and replica methods - to analyze the achievability and computational tractability of the inference problems in the setting of Bayes-optimal inference, which amounts to assuming that the two matrices have random independent elements generated from some known distribution, and this information is available to the inference algorithm.
Sample Complexity of Bayesian Optimal Dictionary Learning
We consider a learning problem of identifying a dictionary matrix D (M times N dimension) from a sample set of M dimensional vectors Y = N^{-1/2} DX, where X is a sparse matrix (N times P dimension) in which the density of non-zero entries is 0<rho< 1.
