Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Semi-Supervised Interpolation in an Anticausal Learning Scenario
Authors: Dominik Janzing, Bernhard Schölkopf
JMLR 2015 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We prove that unlabelled data help for the problem of interpolating a monotonically increasing function if and only if the orthogonality conditions are violated which we only expect for the anticausal direction. Here, performance of SSL and its supervised baseline analogue is measured in terms of two different loss functions: first, the mean squared error and second the surprise in a Bayesian prediction scenario. ... The main contribution of this paper is to describe the relation between the performance of SSL to a mathematically well-defined notion of dependence between PX and PY |X. ... We prove that unlabelled data help for the problem of interpolating a monotonically increasing function... |
| Researcher Affiliation | Academia | Dominik Janzing EMAIL Bernhard Sch olkopf EMAIL Max Planck Institute for Intelligent Systems Spemannstr. 38 72076 T ubingen, Germany |
| Pseudocode | No | The paper primarily presents mathematical definitions, lemmas, theorems, and proofs. There are no explicitly labeled pseudocode blocks or algorithm sections. |
| Open Source Code | No | The paper does not contain any statements about code release, links to source code repositories, or mentions of code in supplementary materials. |
| Open Datasets | No | The paper introduces a theoretical 'simple interpolation problem: Let X and Y be random variables attaining values in [0, 1], deterministically related by Y = f(X)'. It does not use or refer to any publicly available external datasets. |
| Dataset Splits | No | The paper is theoretical and does not conduct experiments on datasets, thus no dataset split information (training/test/validation) is provided. |
| Hardware Specification | No | The paper describes theoretical concepts and mathematical proofs, not empirical experiments that would require specific hardware. Therefore, no hardware specifications are mentioned. |
| Software Dependencies | No | The paper is theoretical and focuses on mathematical models and proofs. It does not describe any implementation or experimental setup that would require specific software libraries or tools with version numbers. |
| Experiment Setup | No | The paper is theoretical and does not describe an experimental setup, hyperparameters, training configurations, or other system-level settings for reproducing experiments. |