Minimax Estimation of Neural Net Distance
Authors: Kaiyi Ji, Yingbin Liang
NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | This paper investigates the minimax estimation problem of the neural net distance based on samples drawn from the distributions. We develop the first known minimax lower bound on the estimation error of the neural net distance, and an upper bound tighter than an existing bound on the estimator error for the empirical neural net distance. Our lower and upper bounds match not only in the order of the sample size but also in terms of the norm of the parameter matrices of neural networks, which justifies the empirical neural net distance as a good approximation of the true neural net distance for training GANs in practice. |
| Researcher Affiliation | Academia | Kaiyi Ji Department of ECE The Ohio State University Columbus, OH 43210 ji.367@osu.edu Yingbin Liang Department of ECE The Ohio State University Columbus, OH 43210 liang.889@osu.edu |
| Pseudocode | No | The paper is theoretical and focuses on mathematical derivations and proofs; it does not include any pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not mention releasing any source code for its methodology. It is a theoretical paper. |
| Open Datasets | No | The paper is theoretical and does not use specific datasets for training or empirical evaluation. It refers to 'samples drawn from distributions µ and ν'. |
| Dataset Splits | No | The paper is theoretical and does not involve empirical experiments with dataset splits for training, validation, or testing. |
| Hardware Specification | No | The paper is theoretical and does not describe any computational experiments or hardware used. |
| Software Dependencies | No | The paper is theoretical and does not mention any software dependencies with version numbers. |
| Experiment Setup | No | The paper is theoretical and does not describe any empirical experiments, hyperparameter values, or specific training configurations. |