Understanding Representation Learnability of Nonlinear Self-Supervised Learning

Authors: Ruofeng Yang, Xiangyuan Li, Bo Jiang, Shuai Li

AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We also present the learning processes and results of the nonlinear SSL and SL model via simulation experiments.
Researcher Affiliation Academia Shanghai Jiao Tong University wanshuiyin@sjtu.edu.cn, lixiangyuan19@sjtu.edu.cn, bjiang@sjtu.edu.cn, shuaili8@sjtu.edu.cn
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks. It describes methods and proofs in prose and mathematical notation.
Open Source Code Yes The codes of this section are available at https://github.com/wanshuiyin/AAAI-2023-The Learnability-of-Nonlinear-SSL.
Open Datasets No The paper designs a "toy data distribution" (Section 3.1) for its experiments and does not use a publicly available dataset with a specific link, DOI, repository name, or formal citation.
Dataset Splits No The paper describes the construction of its custom data distribution but does not specify any training, validation, or test dataset splits.
Hardware Specification Yes All experiments are conduct on a desktop with AMD Ryzen 7 5800H with Radeon Graphics 3.20 GHz and 16 GB memory.
Software Dependencies No The paper does not specify any software dependencies with version numbers (e.g., specific Python libraries like PyTorch or TensorFlow versions) used for the experiments.
Experiment Setup Yes In this section, we choose τ = 7, d = 10, ρ = 1/d1.5, α = 1/800, n = d2 and learning rate η = 0.001 if we do not specify otherwise. Experiments are averaged over 20 random seeds, and we show the average results with 95% confidence interval for learning curves.