Skip to content

Fix bounds errors in default x_abschange and x_relchange #1222

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
pkofod merged 2 commits into from
Dec 7, 2025
+45 −32
Merged

Fix bounds errors in default x_abschange and x_relchange #1222

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e394c23
Fix bounds errors in default `x_abschange` and `x_relchange`
devmotion Dec 6, 2025
8b91563
Add code comment
devmotion Dec 7, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion src/Optim.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -146,7 +146,6 @@ include("multivariate/precon.jl") # preconditioning functionality

# utilities
include("utilities/generic.jl") # generic utilities
include("utilities/maxdiff.jl") # find largest difference
include("utilities/update.jl") # trace code

# Unconstrained optimization
Expand Down
21 changes: 19 additions & 2 deletions src/utilities/assess_convergence.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,9 +4,26 @@ f_relchange(state::AbstractOptimizerState) = f_relchange(state.f_x, state.f_x_pr
f_relchange(f_x, f_x_previous) = abs(f_x - f_x_previous) / abs(f_x)

x_abschange(state::AbstractOptimizerState) = x_abschange(state.x, state.x_previous)
x_abschange(x, x_previous) = maxdiff(x, x_previous)
x_abschange(x::AbstractArray{<:Number}, x_previous::AbstractArray{<:Number}) = Linfdist(x, x_previous)
x_relchange(state::AbstractOptimizerState) = x_relchange(state.x, state.x_previous)
x_relchange(x, x_previous) = maxdiff(x, x_previous) / Base.maximum(abs, x) # Base.maximum !== maximum
x_relchange(x::AbstractArray{<:Number}, x_previous::AbstractArray{<:Number}) = Linfdist(x, x_previous) / Base.maximum(abs, x) # Base.maximum !== maximum

# Copied and adapted from https://github.com/JuliaStats/StatsBase.jl/blob/d70c4a203177c79d851c1cdca450bc6dbd2a4683/src/deviation.jl#L100-L110
# Linfdist(a, b)
#
# Compute the L∞ distance, also called the Chebyshev distance, between
# two arrays: ``\\max_{1≤i≤n} |a_i - b_i|``.
# Efficient equivalent of `maximum(abs, a - b)`.
function Linfdist(x::AbstractArray{<:Number}, y::AbstractArray{<:Number})
n = length(x)
length(y) == n || throw(DimensionMismatch("Inconsistent array lengths."))
if iszero(n)
return zero(abs(zero(eltype(x)) - zero(eltype(y))))
else
broadcasted = Broadcast.broadcasted((xi, yi) -> abs(xi - yi), vec(x), vec(y))
return Base.maximum(Broadcast.instantiate(broadcasted)) # Base.maximum !== maximum
end
end

g_residual(state::NelderMeadState) = state.nm_x
g_residual(state::ZerothOrderState) = oftype(state.f_x, NaN)
Expand Down
16 changes: 0 additions & 16 deletions src/utilities/maxdiff.jl
View file
Open in desktop

This file was deleted.

39 changes: 26 additions & 13 deletions test/general/convergence.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,17 +1,16 @@
mutable struct DummyState <: Optim.AbstractOptimizerState
x::Any
x_previous::Any
f_x::Any
f_x_previous::Any
g_x::Any
mutable struct DummyState{TX,TF,TG} <: Optim.AbstractOptimizerState
x::TX
x_previous::TX
f_x::TF
f_x_previous::TF
g_x::TG
end

mutable struct DummyStateZeroth <: Optim.ZerothOrderState
x::Any
x_previous::Any
f_x::Any
f_x_previous::Any
g_x::Any
mutable struct DummyStateZeroth{TX,TF} <: Optim.ZerothOrderState
x::TX
x_previous::TX
f_x::TF
f_x_previous::TF
end

mutable struct DummyOptions
Expand Down Expand Up @@ -81,7 +80,7 @@ mutable struct DummyMethodZeroth <: Optim.ZerothOrderOptimizer end
@test Optim.initial_convergence(ds, opt) == (true, false)

# Zeroth order methods have no gradient -> returns false by default
ds = DummyStateZeroth(x1, x0, f1, f0, g)
ds = DummyStateZeroth(x1, x0, f1, f0)
dm = DummyMethodZeroth()

x = ones(2)
Expand All @@ -92,4 +91,18 @@ mutable struct DummyMethodZeroth <: Optim.ZerothOrderOptimizer end

# should check all other methods as well

for T in (Float32, Float64)
ds = DummyState(T[-1.3, 2.5, -4.1], T[-1.1, 2.8, -4.0], f_x, f0, zeros(3))
@test @inferred(Optim.x_abschange(ds))::T ≈ 0.3
@test iszero((s -> @allocated(Optim.x_abschange(s)))(ds))
@test @inferred(Optim.x_relchange(ds))::T ≈ 0.3 / 4.1
@test iszero((s -> @allocated(Optim.x_relchange(s)))(ds))

# Special case: Empty state
ds = DummyState(T[], T[], f_x, f0, empty(g_x))
@test iszero(@inferred(Optim.x_abschange(ds))::T)
@test iszero((s -> @allocated(Optim.x_abschange(s)))(ds))
@test isnan(@inferred(Optim.x_relchange(ds))::T)
@test iszero((s -> @allocated(Optim.x_relchange(s)))(ds))
end
end
Loading