Analysis of Krylov Subspace Solutions of Regularized Non-Convex Quadratic Problems
Authors: Yair Carmon, John C. Duchi
NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | 5 Numerical experiments. To see whether our analysis applies to non-worst case problem instances, we generate 5,000 random cubic-regularization problems with d = 10^6 and controlled condition number = (λmax + kscr? k)/(λmin + kscr? k) (see Section E in the supplement for more details). We repeat the experiment three times with different values of and summarize the results in Figure 1a. |
| Researcher Affiliation | Academia | Yair Carmon Department of Electrical Engineering Stanford University yairc@stanford.edu John C. Duchi Departments of Statitstics and Electrical Engineering Stanford University jduchi@stanford.edu |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any information or links regarding the availability of its source code. |
| Open Datasets | No | The paper states "we generate 5,000 random cubic-regularization problems" but does not provide concrete access information or citations to publicly available datasets. |
| Dataset Splits | No | The paper does not describe specific training, validation, or test dataset splits. |
| Hardware Specification | No | The paper does not specify any hardware details (e.g., GPU/CPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers. |
| Experiment Setup | No | The paper describes generating problems with d=10^6 and controlled condition numbers for experiments, and mentions iteration counts like '20 Lanczos iterations' or '100 iterations'. However, it does not provide specific experimental setup details such as hyperparameters (e.g., learning rates, batch sizes, optimizer settings) or other system-level training configurations typically found in such sections. |