Skip to content

test: drop flaky joint-vs-single assertion in LPV multi-dataset test #199

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
baggepinnen merged 1 commit into from
Jun 5, 2026
Merged

test: drop flaky joint-vs-single assertion in LPV multi-dataset test #199

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
12 changes: 0 additions & 12 deletions test/test_lpv.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -131,18 +131,6 @@ end
e2 = mean(abs2, d2.y .- ControlSystemIdentification.predict(sys_joint, d2, λ2; x0 = x0_mat[:, 2]))
@test e1 < 0.05
@test e2 < 0.05

# Joint fit must beat a single-dataset fit on the OTHER experiment, since
# the single fit overfits its own dataset's input/noise realization.
res1 = lpv_pem(d1, λ1, 2; basis,
K0 = 1e-6 .* ones(2, 1),
show_trace = false, store_trace = false,
iterations = 200, time_limit = 60)
sys_only1, x0_only1, _ = res1
# Held-out prediction using sys_only1 starts from zero state, which is fair
# since it never saw d2.
e2_only1 = mean(abs2, d2.y .- ControlSystemIdentification.predict(sys_only1, d2, λ2))
@test e1 < e2_only1
end

@testset "LPV PEM basis-of-length-1 ≈ LTI" begin
Expand Down
Loading