new optional parameter for subset selection

Author: BatyLeo

docs/make.jl

@@ -9,9 +9,13 @@ tutorial_dir = joinpath(@__DIR__, "src", "tutorials")
 tutorial_files = readdir(tutorial_dir)
 md_tutorial_files = [split(file, ".")[1] * ".md" for file in tutorial_files]
 
-for file in tutorial_files
-    filepath = joinpath(tutorial_dir, file)
-    Literate.markdown(filepath, md_dir; documenter=true, execute=false)
+include_tutorial = false
+
+if include_tutorial
+    for file in tutorial_files
+        filepath = joinpath(tutorial_dir, file)
+        Literate.markdown(filepath, md_dir; documenter=true, execute=false)
+    end
 end
 
 makedocs(;
@@ -21,7 +25,7 @@ makedocs(;
     format=Documenter.HTML(),
     pages=[
         "Home" => "index.md",
-        # "Tutorials" => md_tutorial_files,
+        "Tutorials" => include_tutorial ? md_tutorial_files : [],
         "Benchmark problems list" => [
             "benchmarks/subset_selection.md",
             "benchmarks/portfolio_optimization.md",
@@ -33,9 +37,11 @@ makedocs(;
     ],
 )
 
-for file in md_tutorial_files
-    filepath = joinpath(md_dir, file)
-    rm(filepath)
+if include_tutorial
+    for file in md_tutorial_files
+        filepath = joinpath(md_dir, file)
+        rm(filepath)
+    end
 end
 
 deploydocs(;

docs/src/benchmarks/subset_selection.md

@@ -1,9 +1,13 @@
 # Subset Selection
 
-[`SubsetSelectionBenchmark`](@ref) is a very simple benchmark problem of subset selection.
+[`SubsetSelectionBenchmark`](@ref) is the most trivial benchmark problem in this package.
+It is minimalistic and serves as a simple example for debugging and testing purposes.
 
-We have a set of ``n`` items, each item having an `unknown' value.
+## Description
+We have a set of ``n`` items, each item having an unknown value.
 We want to select a subset of ``k`` items that maximizes the sum of the values of the selected items.
 
-As input, we are given a feature vector, that contains exactly the value of each item.
-The goal is to learn the identity mapping between the feature vector and the value of the items.
+As input, instead of the items costs, we are given a feature vector, such that an unknown linear mapping between the feature vector and the value of the items exists.
+
+By default, this linear mapping is the identity mapping, i.e., the value of each item is equal to the value of the corresponding feature vector element.
+However, this mapping can be changed by setting the `identity_mapping` parameter to false.

src/SubsetSelection/SubsetSelection.jl

@@ -58,13 +58,21 @@ Generate a dataset of labeled instances for the subset selection problem.
 The mapping between features and cost is identity.
 """
 function Utils.generate_dataset(
-    bench::SubsetSelectionBenchmark, dataset_size::Int=10; seed::Int=0
+    bench::SubsetSelectionBenchmark,
+    dataset_size::Int=10;
+    seed::Int=0,
+    identity_mapping=true,
 )
     (; n, k) = bench
     rng = MersenneTwister(seed)
     features = [randn(rng, Float32, n) for _ in 1:dataset_size]
-    costs = copy(features)  # we assume that the cost is the same as the feature
-    solutions = top_k.(features, k)
+    costs = if identity_mapping
+        copy(features)  # we assume that the cost is the same as the feature
+    else
+        mapping = Dense(n => n; bias=false)
+        mapping.(features)
+    end
+    solutions = top_k.(costs, k)
     return [DataSample(; x=x, θ=θ, y=y) for (x, θ, y) in zip(features, costs, solutions)]
 end