szcf-weiya

Results 91 comments of szcf-weiya

Thanks for pointing. I think they are the same website, just use a new domain. Just had a try, https://web.stanford.edu/~hastie would be automatically redirected to https://hastie.su.domains/

after rewriting the testing error, the pattern of `p = 20` can be reproduced, ![p20](https://user-images.githubusercontent.com/13688320/137603715-3e3c60fa-6d76-4c40-b08a-2026c338dbe9.png) p = 100 cannot completely be reproduced, but if adjust the minimum `lambda`, then it...

tried different ways to calculate SNR - empirical from `Xbeta` - use `var(Xbeta)` formula, as also used in https://cran.r-project.org/web/packages/bestridge/vignettes/An-introduction-to-bestridge.html ![image](https://user-images.githubusercontent.com/13688320/137603843-22cc5da3-7704-44cb-81e3-f92c15d89655.png) - treat x individually, as in https://esl.hohoweiya.xyz/03-Linear-Methods-for-Regression/3.3-Subset-Selection/index.html ![image](https://user-images.githubusercontent.com/13688320/137603857-b81ff710-5031-4737-9dfc-db75a8b215a9.png) but the...

tried different SNR levels with the approach `beta Sigma beta`, it seems that a low SNR tends to reproduce the decreasing pattern. ![image](https://user-images.githubusercontent.com/13688320/137604045-39cf1124-ff31-471c-b6b1-f5c6917a88e4.png) ![image](https://user-images.githubusercontent.com/13688320/137604046-f5dec5cb-4f1d-4616-9dce-24f6599e5086.png) ![image](https://user-images.githubusercontent.com/13688320/137604049-8df22afe-f329-495c-95db-8a49cbcfeda9.png) ![image](https://user-images.githubusercontent.com/13688320/137604051-91686627-5fd5-492b-a152-0302501d8da5.png) ![image](https://user-images.githubusercontent.com/13688320/137604053-9deb6535-2d86-4458-8090-c7c0115d4f64.png)

also tried different lambdas given SNR = 2, but no changes ```julia julia> run(p = 1000, nrep=100, λs = [0.001, 5000, 10000], snr = 2) ``` ![image](https://user-images.githubusercontent.com/13688320/137604075-0960f355-a966-4839-ba1f-cf6717b10406.png)

larger `p` does not reproduce, either. ```julia julia> run(p = 5000, nrep=100, λs = [0.001, 100, 1000], snr = 2) ``` ![image](https://user-images.githubusercontent.com/13688320/137606496-7b7d2bf6-76bc-4781-8bbb-b79aa29ff5cc.png)

The following calculation assumes `R_m` is fixed, but I think it should not be fixed (see the following first several sentences). However, I failed to obtain a closed form when...

## binary greedy partition (without pruning) for simplicity, I wrote a no-pruning version from scratch, ```julia julia> includet("df_regtree.jl") julia> [rep_calc_df(maxdepth=i) for i=0:4] 5-element Vector{Tuple{Float64, Float64}}: (1.080629443872466, 0.041187110826985264) (9.996914473623567, 0.11093327184178654) (21.34913882167176,...

## call `tree::prune.tree` to return a tree with the given number of terminal nodes, I call `tree::prune.tree`, which has an argument `best` to specify the number of terminal nodes, but...