Logarithmic Pruning is All You Need
Authors: Laurent Orseau, Marcus Hutter, Omar Rivasplata
NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | Building on top of these previous works, we aim at providing stronger theoretical guarantees still based on the motto that pruning is all you need but hoping to provide further insights into how winning tickets may be found. In this work we relax the aforementioned assumptions while greatly strengthening the theoretical guarantees by improving from polynomial to logarithmic order in all variables except the depth, for the number of samples required to approximate one target weight. |
| Researcher Affiliation | Industry | Laurent Orseau Deep Mind, London, UK lorseau@google.com Marcus Hutter Deep Mind, London, UK www.hutter1.net Omar Rivasplata Deep Mind, London, UK rivasplata@google.com |
| Pseudocode | No | The paper describes mathematical constructions and theoretical proofs but does not include any explicitly labeled pseudocode blocks or algorithms. |
| Open Source Code | No | The paper does not contain any statement about making its code open source or providing a link to a code repository. |
| Open Datasets | No | This paper is theoretical and does not conduct experiments involving datasets. While it mentions previous work with datasets like vision, speech synthesis, and games, it does not use or make its own dataset available. |
| Dataset Splits | No | The paper is theoretical and does not involve empirical experiments requiring dataset splits for validation. No training/test/validation splits are discussed. |
| Hardware Specification | No | The paper is theoretical and does not describe any experiments that would require specific hardware. Thus, no hardware specifications are mentioned. |
| Software Dependencies | No | The paper is theoretical and does not mention any specific software dependencies with version numbers for experimental setup or implementation. |
| Experiment Setup | No | The paper is theoretical and focuses on mathematical proofs and bounds rather than practical implementation details or experimental setups. Therefore, no hyperparameters or specific training configurations are provided. |