RECORD
Independence Tests Without Ground Truth for Noisy Learners
Machine Learning · Submitted 28 Oct 2020
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim We discuss how to use the closed form solution to create a self-consistent test that can validate the independence assumption itself absent the correct labels ground truth.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Exact ground truth invariant polynomial systems can be written for arbitrarily correlated binary classifiers. Their solutions give estimates for sample statistics that require knowledge of the ground truth of the correct labels in the sample. Of these polynomial systems, only a few have been solved in closed form. Here we discuss the exact solution for independent binary classifiers - resolving an outstanding problem that has been presented at this conference and others. Its practical applicability is hampered by its sole remaining assumption - the classifiers need to be independent in their sample errors. We discuss how to use the closed form solution to create a self-consistent test that can validate the independence assumption itself absent the correct labels ground truth. It can be cast as an algebraic geometry conjecture for binary classifiers that remains unsolved. A similar conjecture for the ground truth invariant algebraic system for scalar regressors is solvable, and we present the solution here. We also discuss experiments on the Penn ML Benchmark classification tasks that provide further evidence that the conjecture may be true for the polynomial system of binary classifiers.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Exact ground truth invariant polynomial systems can be written for arbitrarily correlated binary classifiers. | background 0.97 | 0.32 | 0.07 | asserted 1.00 |
| s1 | Their solutions give estimates for sample statistics that require knowledge of the ground truth of the correct labels in the sample. | background 0.90 | 0.15 | 0.03 | asserted 1.00 |
| s2 | Of these polynomial systems, only a few have been solved in closed form. | background 0.64 | 0.10 | 0.03 | asserted 1.00 |
| s3 | Here we discuss the exact solution for independent binary classifiers - resolving an outstanding problem that has been presented at this conference and others. | contribution 0.91 | 0.64 | 0.17 | asserted 0.99 |
| s4 | Its practical applicability is hampered by its sole remaining assumption - the classifiers need to be independent in their sample errors. | limitation 0.97 | 0.30 | 0.08 | asserted 1.00 |
| s5 | We discuss how to use the closed form solution to create a self-consistent test that can validate the independence assumption itself absent the correct labels ground truth. | contribution 0.78 | 0.80 | 0.54 | asserted 0.90 |
| s6 | It can be cast as an algebraic geometry conjecture for binary classifiers that remains unsolved. | gap 0.55 | 0.27 | 0.08 | asserted 0.81 |
| s7 | A similar conjecture for the ground truth invariant algebraic system for scalar regressors is solvable, and we present the solution here. | contribution 0.82 | 0.90 | 0.13 | asserted 1.00 |
| s8 | We also discuss experiments on the Penn ML Benchmark classification tasks that provide further evidence that the conjecture may be true for the polynomial system of binary classifiers. | result 0.62 | 0.93 | 0.12 | hedged possibility 0.99 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Exact ground truth invariant polynomial systems can be written for arbitrarily correlated binary classifiers. Their solutions give estimates for sample statistics that require knowledge of the ground truth of the correct labels in the sample. Of these polynomial systems, only a few have been solved in closed form. Here we discuss the exact solution for independent binary classifiers - resolving an outstanding problem that has been presented at this conference and others. Its practical applicability is hampered by its sole remaining assumption - the classifiers need to be independent in their sample errors. We discuss how to use the closed form solution to create a self-consistent test that can validate the independence assumption itself absent the correct labels ground truth. It can be cast as an algebraic geometry conjecture for binary classifiers that remains unsolved. A similar conjecture for the ground truth invariant algebraic system for scalar regressors is solvable, and we present the solution here. We also discuss experiments on the Penn ML Benchmark classification tasks that provide further evidence that the conjecture may be true for the polynomial system of binary classifiers.
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.