Cslib.MachineLearning.PACLearning.hypothesisError
defimported Lean
The *symmetric-difference error* of a hypothesis h with respect to a target concept c (both viewed as subsets of α) under distribution P, defined as P(h ∆ c).
Statement
set_option autoImplicit true in set_option relaxedAutoImplicit true in open MeasureTheory Set in open scoped ENNReal NNReal in variable {α : Type*} [MeasurableSpace α] in noncomputable def Cslib.MachineLearning.PACLearning.hypothesisError (P : Measure α) (h c : Set α) : ℝ≥0∞
- Defined in
- CSLib, `Cslib.MachineLearning.PACLearning.hypothesisError`
- Lean proof
- By Samuel Schlesinger, from github.com/leanprover/cslib at
3951377e5a3f(Copyright (c) 2026 Samuel Schlesinger. All rights reserved, Apache-2.0). Compiled here against leanprover/lean4:v4.33.1, Mathlib v4.33.1; written for leanprover/lean4:v4.33.0.Cslib.MachineLearning.PACLearning.hypothesisError← Cslib.MachineLearning.PACLearning.hypothesisError (Cslib/MachineLearning/PACLearning/Defs.lean:485): verbatim
- Verified
- 08 Oct 2026
- Axioms
- none listed
- Used by 2
- Cslib.MachineLearning.PACLearning.hypothesisError_eq_addThe total hypothesis error decomposes as the sum of false positive and false negative errors, since
h ∆ c = (h \ c) ∪ (c \ h)is a… - Cslib.MachineLearning.PACLearning.error_map_eq_hypothesisErrorUnder a realizable distribution
P.map (x ↦ (x, c(x))), the general 0-1errorcoincides with the binaryhypothesisError P h c, where…
- Cslib.MachineLearning.PACLearning.hypothesisError_eq_addThe total hypothesis error decomposes as the sum of false positive and false negative errors, since
Lean source view module on GitHub
set_option autoImplicit true in set_option relaxedAutoImplicit true in open MeasureTheory Set in open scoped ENNReal NNReal in variable {α : Type*} [MeasurableSpace α] in /-- The *symmetric-difference error* of a hypothesis `h` with respect to a target concept `c` (both viewed as subsets of `α`) under distribution `P`, defined as `P(h ∆ c)`. -/ noncomputable def Cslib.MachineLearning.PACLearning.hypothesisError (P : Measure α) (h c : Set α) : ℝ≥0∞ := P (symmDiff h c)