diff --git a/docs/Project.toml b/docs/Project.toml
index fcfaedc76..5f0b7d003 100644
--- a/docs/Project.toml
+++ b/docs/Project.toml
@@ -1,5 +1,6 @@
 [deps]
 AmplNLWriter = "7c4d4715-977e-5154-bfe0-e096adeac482"
+ComponentArrays = "b0b7db55-cfe3-40fc-9ded-d10e2dbeff66"
 Documenter = "e30172f5-a6a5-5a46-863b-614d45cd2de4"
 FiniteDiff = "6a86dc24-6348-571c-b903-95158fe2bd41"
 ForwardDiff = "f6369f11-7733-5829-9624-2563aa707210"
@@ -11,6 +12,7 @@ Juniper = "2ddba703-00a4-53a7-87a5-e8b9971dde84"
 Lux = "b2108857-7c20-44ae-9111-449ecde12c47"
 Manifolds = "1cead3c2-87b3-11e9-0ccd-23c62b72b94e"
 Manopt = "0fc0a36d-df90-57f3-8f93-d78a9fc72bb5"
+MLUtils = "f1d291b0-491e-4a28-83b9-f70985020b54"
 ModelingToolkit = "961ee093-0014-501f-94e3-6117800e7a78"
 NLPModels = "a4795742-8479-5a88-8948-cc11e1c8c1a6"
 NLPModelsTest = "7998695d-6960-4d3a-85c4-e1bceb8cd856"
@@ -33,6 +35,8 @@ OptimizationPRIMA = "72f8369c-a2ea-4298-9126-56167ce9cbc2"
 OptimizationPolyalgorithms = "500b13db-7e66-49ce-bda4-eed966be6282"
 OptimizationSpeedMapping = "3d669222-0d7d-4eb9-8a9f-d8528b0d9b91"
 OrdinaryDiffEq = "1dea7af3-3e70-54e6-95c3-0bf5283fa5ed"
+Plots = "91a5bcdd-55d7-5caf-9e0b-520d859cae80"
+Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
 ReverseDiff = "37e2e3b7-166d-5795-8a7a-e32c996b4267"
 SciMLBase = "0bca4576-84f4-4d90-8ffe-ffa030f20462"
 SciMLSensitivity = "1ed8b502-d754-442c-8d5d-10ac956f44a1"
@@ -43,6 +47,7 @@ Zygote = "e88e6eb3-aa80-5325-afca-941959d7151f"
 
 [compat]
 AmplNLWriter = "1"
+ComponentArrays = "0.15"
 Documenter = "1"
 FiniteDiff = ">= 2.8.1"
 ForwardDiff = ">= 0.10.19"
@@ -53,6 +58,7 @@ Juniper = "0.9"
 Lux = "1"
 Manifolds = "0.9"
 Manopt = "0.4"
+MLUtils = "0.4.4"
 ModelingToolkit = "9"
 NLPModels = "0.21"
 NLPModelsTest = "0.10"
@@ -75,6 +81,8 @@ OptimizationPRIMA = "0.3"
 OptimizationPolyalgorithms = "0.3"
 OptimizationSpeedMapping = "0.3"
 OrdinaryDiffEq = "6"
+Plots = "1"
+Random = "1"
 ReverseDiff = ">= 1.9.0"
 SciMLBase = "2.30.0"
 SciMLSensitivity = "7"
diff --git a/docs/src/optimization_packages/optimization.md b/docs/src/optimization_packages/optimization.md
index 66d108653..22a43d872 100644
--- a/docs/src/optimization_packages/optimization.md
+++ b/docs/src/optimization_packages/optimization.md
@@ -63,7 +63,7 @@ res = solve(prob, Optimization.LBFGS(), maxiters = 100)
 
 ```@example Sophia
 
-using Optimization, Lux, Zygote, MLUtils, Statistics, Plots
+using Optimization, Lux, Zygote, MLUtils, Statistics, Plots, Random, ComponentArrays
 
 x = rand(10000)
 y = sin.(x)
diff --git a/docs/src/tutorials/minibatch.md b/docs/src/tutorials/minibatch.md
index 3604d78f6..80784da98 100644
--- a/docs/src/tutorials/minibatch.md
+++ b/docs/src/tutorials/minibatch.md
@@ -9,7 +9,8 @@ It is possible to solve an optimization problem with batches using a `MLUtils.Da
 
 ```@example minibatch
 
-using Lux, Optimization, OptimizationOptimisers, OrdinaryDiffEq, SciMLSensitivity, MLUtils
+using Lux, Optimization, OptimizationOptimisers, OrdinaryDiffEq, SciMLSensitivity, MLUtils,
+      Random, ComponentArrays
 
 function newtons_cooling(du, u, p, t)
     temp = u[1]
@@ -67,7 +68,7 @@ k = 10
 train_loader = MLUtils.DataLoader((ode_data, t), batchsize = k)
 
 numEpochs = 300
-l1 = loss_adjoint(pp, train_loader.data)[1]
+l1 = loss_adjoint(ps_ca, train_loader.data)[1]
 
 optfun = OptimizationFunction(
     loss_adjoint,