Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
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.
On the Variance, Admissibility, and Stability of Empirical Risk Minimization
Authors: Gil Kur, Eli Putterman, Alexander Rakhlin
NeurIPS 2023 | Venue PDF | LLM Run Details | Input Tokens: 18,473 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 3,243 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this paper, we prove that, under relatively mild assumptions, the suboptimality of ERM must be due to its bias. Namely, the variance error term of ERM (in terms of the bias and variance decomposition) enjoys the minimax rate. |
| Researcher Affiliation | Academia | Gil Kur EECS MIT EMAIL Eli Putterman Mathematics Department Tel Aviv University EMAIL Alexandrer Rakhlin BCS & IDSS MIT EMAIL |
| Pseudocode | No | The paper does not contain any pseudocode or clearly labeled algorithm blocks. |
| Open Source Code | No | The paper does not provide any statement or link regarding the availability of open-source code for the methodology described. |
| Open Datasets | No | The paper is theoretical and focuses on mathematical proofs and characterizations. It does not refer to specific datasets used for training, validation, or testing. |
| Dataset Splits | No | The paper is theoretical and focuses on mathematical proofs and characterizations. It does not provide details on training/test/validation dataset splits. |
| Hardware Specification | No | The paper does not mention any specific hardware used for running experiments. This is consistent with its theoretical nature. |
| Software Dependencies | No | The paper does not provide details about specific software dependencies with version numbers. This is consistent with its theoretical nature. |
| Experiment Setup | No | The paper is theoretical and does not describe any experimental setup details such as hyperparameters or system-level training settings. |