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].
Robust Meta-learning for Mixed Linear Regression with Small Batches
Authors: Weihao Kong, Raghav Somani, Sham Kakade, Sewoong Oh
NeurIPS 2020 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Simulation results supporting our theoretical prediction are shown in Fig. 2. For the analysis and the experimental setup we refer to K. |
| Researcher Affiliation | Collaboration | EMAIL. University of Washington EMAIL. University of Washington EMAIL. University of Washington & Microsoft Research EMAIL. University of Washington |
| Pseudocode | Yes | Algorithm 1 Meta-learning ... Algorithm 2 Robust subspace estimation ... Algorithm 3 Double-Filtering |
| Open Source Code | No | The paper does not provide any statement or link regarding the availability of its source code. |
| Open Datasets | No | The paper describes a generative model for synthetic data (e.g., 'xi,j N(0, Id) and ϵi,j N(0, σ2 i )') and refers to 'meta-train dataset' as a collection of tasks. It does not mention the use of any specific publicly available datasets with concrete access information for training. |
| Dataset Splits | No | The paper describes theoretical data batches (DL1, DL2, DH) for analysis and refers to 'achievable accuracy' in theoretical terms, but does not provide details on empirical train/validation/test splits used for experimental reproduction. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware (e.g., GPU, CPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific software names with version numbers (e.g., programming languages, libraries, frameworks) used for the experiments. |
| Experiment Setup | No | The paper mentions 'For the analysis and the experimental setup we refer to K.' (Section K is in the supplementary material and not provided). Without access to Section K, no specific hyperparameters, training configurations, or system-level settings are detailed in the main text. |