Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates
Authors: Steve Chien, Prateek Jain, Walid Krichene, Steffen Rendle, Shuang Song, Abhradeep Thakurta, Li Zhang
ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive validation on standard benchmarks demonstrate that the algorithm, in combination with carefully designed sampling procedures, is significantly more accurate than existing techniques, thus promising to be the first practical DP embedding model. |
| Researcher Affiliation | Industry | 1Google Research. Correspondence to: Walid Krichene <walidk@google.com>, Abhradeep Thakurta <athakurta@google.com>. |
| Pseudocode | Yes | Algorithm 1 DPALS: Private Matrix Completion via Alternating Minimization |
| Open Source Code | No | The paper does not provide a direct link or explicit statement about the availability of its source code. |
| Open Datasets | Yes | Movie Lens data sets. We apply our method to two common recommender benchmarks: (i) rating prediction on Movie Lens 10M (ML-10M) following Lee et al. (2013), where the task is to predict the value of a user s rating, and performance is measured using the RMSE, (ii) item recommendation on Movie Lens 20M (ML-20M) following Liang et al. (2018), where the task is to select k movies for each user and performance is measured using Recall@k. |
| Dataset Splits | No | Each data set is partitioned into training, validation and test sets. Hyper-parameters are chosen on the validation set, and the final performance is measured on the test set. However, the paper does not specify the exact percentages or methodology for these splits. |
| Hardware Specification | No | The paper does not specify any particular hardware used for running experiments (e.g., GPU models, CPU types). |
| Software Dependencies | No | The paper does not provide specific version numbers for any software dependencies. |
| Experiment Setup | Yes | Additional details on the experimental setup are in Appendix D, including statistics of the data sets, a list of hyper-parameters and the ranges we used for each. |