Skip to main content

Source-pinned research

Research proof index

Search theorem names, mathematical ideas, modules, topics, projects, and role-labelled researchers. Open a result for its complete indexed Lean declaration and source record.

This index contains 2,569 curated research declarations and 119,070 complete package declarations. Search 10,000 more complete Mathlib declarations.

All topics

Showing 655 to 660 of 2,569 results.

Project-declaredLean 4.33.0-rc1

Totalize nonsink mtr iff

Cslib.LTS.totalize.nonsink_mtr_iff

Mathematical statement

In totalize, the multistep transitions between non-sink states correspond exactly to the multistep transitions in the original LTS.

computer sciencecomputabilityprogram semantics

Source project: Lean Computer Science Library

Person-level attribution pending.

View proof record
Project-declaredLean 4.33.0-rc1

Ae mem version Space of realizable

Cslib.MachineLearning.PACLearning.ae_mem_versionSpace_of_realizable

Mathematical statement

Under iid sampling from the realizable joint distribution induced by c ∈ C and a probability measure P on α, the target concept c lies in the version space almost surely.

computer sciencecomputabilityprogram semantics

Source project: Lean Computer Science Library

Person-level attribution pending.

View proof record
Project-declaredLean 4.33.0-rc1

Empirical Error eq div

Cslib.MachineLearning.PACLearning.empiricalError_eq_div

Mathematical statement

The empirical 0-1 error equals the empirical miscount divided by the sample size.

computer sciencecomputabilityprogram semantics

Source project: Lean Computer Science Library

Person-level attribution pending.

View proof record
Project-declaredLean 4.33.0-rc1

Error map eq hypothesis Error

Cslib.MachineLearning.PACLearning.error_map_eq_hypothesisError

Mathematical statement

Under a realizable distribution P.map (x ↦ (x, c(x))), the general 0-1 error coincides with the binary hypothesisError P h c, where h and c are viewed as subsets of α via the characteristic function decide (· ∈ ·).

computer sciencecomputabilityprogram semantics

Source project: Lean Computer Science Library

Person-level attribution pending.

View proof record
Project-declaredLean 4.33.0-rc1

Is PACLearner For antitone C

Cslib.MachineLearning.PACLearning.IsPACLearnerFor.antitone_C

Mathematical statement

The deterministic PAC learner predicate is antitone in the concept class: a learner for a larger class C' is also a learner for any subclass C ⊆ C', since the agnostic benchmark optimalError _ C ≥ optimalError _ C' makes the error requirement easier.

computer sciencecomputabilityprogram semantics

Source project: Lean Computer Science Library

Person-level attribution pending.

View proof record