DFSane non-allocating for scalars now

Author: avik-pal

Project.toml

@@ -20,9 +20,11 @@ StaticArraysCore = "1e83bf80-4336-4d27-bf5d-d5a4f845583c"
 
 [weakdeps]
 PolyesterForwardDiff = "98d1487c-24ca-40b6-b7ab-df2af84e126b"
+StaticArrays = "90137ffa-7385-5640-81b9-e52037218182"
 
 [extensions]
 SimpleNonlinearSolvePolyesterForwardDiffExt = "PolyesterForwardDiff"
+SimpleNonlinearSolveStaticArraysExt = "StaticArrays"
 
 [compat]
 ADTypes = "0.2.6"
@@ -38,4 +40,5 @@ PrecompileTools = "1"
 Reexport = "1"
 SciMLBase = "2.7"
 StaticArraysCore = "1.4"
+StaticArrays = "1"
 julia = "1.9"

ext/SimpleNonlinearSolveStaticArraysExt.jl

@@ -0,0 +1,7 @@
+module SimpleNonlinearSolveStaticArraysExt
+
+using SimpleNonlinearSolve
+
+@inline SimpleNonlinearSolve.__is_extension_loaded(::Val{:StaticArrays}) = true
+
+end

src/linesearch.jl

@@ -37,7 +37,8 @@ end
 end
 
 (alg::LiFukushimaLineSearch)(prob, fu, u) = __generic_init(alg, prob, fu, u)
-function (alg::LiFukushimaLineSearch)(prob, fu::SArray, u::SArray)
+function (alg::LiFukushimaLineSearch)(prob, fu::Union{Number, SArray},
+        u::Union{Number, SArray})
     (alg.nan_maxiters === missing || alg.nan_maxiters === nothing) &&
         return __static_init(alg, prob, fu, u)
     @warn "`LiFukushimaLineSearch` with NaN checking is not non-allocating" maxlog=1

src/nlsolve/dfsane.jl

@@ -9,29 +9,29 @@ see the paper [1].
 
 ### Keyword Arguments
 
-  - `σ_min`: the minimum value of the spectral coefficient `σ_k` which is related to the step
-    size in the algorithm. Defaults to `1e-10`.
-  - `σ_max`: the maximum value of the spectral coefficient `σ_k` which is related to the step
-    size in the algorithm. Defaults to `1e10`.
+  - `σ_min`: the minimum value of the spectral coefficient `σ_k` which is related to the
+    step size in the algorithm. Defaults to `1e-10`.
+  - `σ_max`: the maximum value of the spectral coefficient `σ_k` which is related to the
+    step size in the algorithm. Defaults to `1e10`.
   - `σ_1`: the initial value of the spectral coefficient `σ_k` which is related to the step
     size in the algorithm.. Defaults to `1.0`.
   - `M`: The monotonicity of the algorithm is determined by a this positive integer.
     A value of 1 for `M` would result in strict monotonicity in the decrease of the L2-norm
-    of the function `f`. However, higher values allow for more flexibility in this reduction.
-    Despite this, the algorithm still ensures global convergence through the use of a
-    non-monotone line-search algorithm that adheres to the Grippo-Lampariello-Lucidi
+    of the function `f`. However, higher values allow for more flexibility in this
+    reduction. Despite this, the algorithm still ensures global convergence through the use
+    of a non-monotone line-search algorithm that adheres to the Grippo-Lampariello-Lucidi
     condition. Values in the range of 5 to 20 are usually sufficient, but some cases may call
     for a higher value of `M`. The default setting is 10.
-  - `γ`: a parameter that influences if a proposed step will be accepted. Higher value of `γ`
-    will make the algorithm more restrictive in accepting steps. Defaults to `1e-4`.
+  - `γ`: a parameter that influences if a proposed step will be accepted. Higher value of
+    `γ` will make the algorithm more restrictive in accepting steps. Defaults to `1e-4`.
   - `τ_min`: if a step is rejected the new step size will get multiplied by factor, and this
     parameter is the minimum value of that factor. Defaults to `0.1`.
   - `τ_max`: if a step is rejected the new step size will get multiplied by factor, and this
     parameter is the maximum value of that factor. Defaults to `0.5`.
   - `nexp`: the exponent of the loss, i.e. ``f_k=||F(x_k)||^{nexp}``. The paper uses
     `nexp ∈ {1,2}`. Defaults to `2`.
   - `η_strategy`:  function to determine the parameter `η_k`, which enables growth
-    of ``||F||^2``. Called as ``η_k = η_strategy(f_1, k, x, F)`` with `f_1` initialized as
+    of ``||F||^2``. Called as `η_k = η_strategy(f_1, k, x, F)` with `f_1` initialized as
     ``f_1=||F(x_1)||^{nexp}``, `k` is the iteration number, `x` is the current `x`-value and
     `F` the current residual. Should satisfy ``η_k > 0`` and ``∑ₖ ηₖ < ∞``. Defaults to
     ``||F||^2 / k^2``.
@@ -83,7 +83,8 @@ function SciMLBase.__solve(prob::NonlinearProblem, alg::SimpleDFSane{M}, args...
     α_1 = one(T)
     f_1 = fx_norm
 
-    history_f_k = if x isa SArray
+    history_f_k = if x isa SArray ||
+                     (x isa Number && __is_extension_loaded(Val(:StaticArrays)))
         ones(SVector{M, T}) * fx_norm
     else
         fill(fx_norm, M)

test/basictests.jl

@@ -158,8 +158,7 @@ end
         @test true
     catch e
         @error e
-        # History Vector Allocates
-        @test false broken=(alg isa SimpleDFSane)
+        @test false
     end
 
     # ForwardDiff allocates for hessian since we don't propagate the chunksize