Pertanyaan yang diberi tag matrix-inverse

11
R / mgcv: Mengapa produk tensor () dan ti () menghasilkan permukaan yang berbeda?

The mgcvpaket untuk Rmemiliki dua fungsi untuk pas interaksi produk tensor: te()dan ti(). Saya memahami pembagian kerja dasar antara keduanya (menyesuaikan interaksi non-linear vs menguraikan interaksi ini menjadi efek utama dan interaksi). Yang tidak saya mengerti adalah mengapa te(x1, x2)dan...

r gam mgcv conditional-probability mixed-model references bayesian estimation conditional-probability machine-learning optimization gradient-descent r hypothesis-testing wilcoxon-mann-whitney time-series bayesian inference change-point time-series anova repeated-measures statistical-significance bayesian contingency-tables regression prediction quantiles classification auc k-means scikit-learn regression spatial circular-statistics t-test effect-size cohens-d r cross-validation feature-selection caret machine-learning modeling python optimization frequentist correlation sample-size normalization group-differences heteroscedasticity independence generalized-least-squares lme4-nlme references mcmc metropolis-hastings optimization r logistic feature-selection separation clustering k-means normal-distribution gaussian-mixture kullback-leibler java spark-mllib data-visualization categorical-data barplot hypothesis-testing statistical-significance chi-squared type-i-and-ii-errors pca scikit-learn conditional-expectation statistical-significance meta-analysis intuition r time-series multivariate-analysis garch machine-learning classification data-mining missing-data cart regression cross-validation matrix-decomposition categorical-data repeated-measures chi-squared assumptions contingency-tables prediction binary-data trend test-for-trend matrix-inverse anova categorical-data regression-coefficients standard-error r distributions exponential interarrival-time copula log-likelihood time-series forecasting prediction-interval mean standard-error meta-analysis meta-regression network-meta-analysis systematic-review normal-distribution multiple-regression generalized-linear-model poisson-distribution poisson-regression r sas cohens-kappa
10
Penjelasan gamblang untuk “stabilitas numerik inversi matriks” dalam regresi ridge dan perannya dalam mengurangi overfit

Saya mengerti bahwa kita dapat menggunakan regularisasi dalam masalah regresi kuadrat terkecil sebagai w∗= argminw[ ( Y - X w )T( y - X w ) + λ ∥ w ∥2]w∗=argminw⁡[(y−Xw)T(y−Xw)+λ‖w‖2]\boldsymbol{w}^* = \operatorname*{argmin}_w \left[ (\mathbf y-\mathbf{Xw})^T(\boldsymbol{y}-\mathbf{Xw}) +...

regression regularization ridge-regression overfitting matrix-inverse