Sample Complexity of Forecast Aggregation
Authors: Tao Lin, Yiling Chen
NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this paper, we initiate the study of sample complexity of forecast aggregation... We show that however, even in this benign model, optimal aggregation in general needs exponentially many samples. ... The main technical part of our paper is to prove the Ω(mn 2/ε) lower bound on the sample complexity of forecast aggregation for the general case, via a reduction from the distribution learning problem. |
| Researcher Affiliation | Academia | Tao Lin Harvard University Cambridge, MA 02138 tlin@g.harvard.edu Yiling Chen Harvard University Cambridge, MA 02138 yiling@seas.harvard.edu |
| Pseudocode | No | The paper does not contain pseudocode or a clearly labeled algorithm block. |
| Open Source Code | No | The paper does not provide an unambiguous statement or link to open-source code for the methodology described. |
| Open Datasets | No | The paper refers to 'past data' and 'historical weather forecasts' as examples but does not specify a particular publicly available dataset or provide access information for any dataset used in their theoretical analysis. |
| Dataset Splits | No | This is a theoretical paper that does not conduct empirical experiments, and therefore does not provide dataset splits for training, validation, or testing. |
| Hardware Specification | No | The paper is theoretical and does not describe any specific hardware used for experiments. |
| Software Dependencies | No | The paper is theoretical and does not mention specific software dependencies with version numbers for experimental reproducibility. |
| Experiment Setup | No | The paper is theoretical and focuses on mathematical proofs and analyses. It does not provide details about an experimental setup, such as hyperparameters or system-level training settings. |