Robust Structured Estimation with Single-Index Models

Authors: Sheng Chen, Arindam Banerjee

ICML 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results are provided to support our theoretical analyses.
Researcher Affiliation Academia 1Department of Computer Science & Engineering, University of Minnesota-Twin Cities, Minnesota, USA. Correspondence to: Sheng Chen <shengc@cs.umn.edu>, Arindam Banerjee <banerjee@cs.umn.edu>.
Pseudocode No The paper describes algorithms using mathematical equations and prose but does not contain structured pseudocode or clearly labeled algorithm blocks.
Open Source Code No The paper does not provide any concrete access to source code, such as a specific repository link or an explicit code release statement.
Open Datasets No The paper states 'Essentially we generate our data (x, y) from y = f ( θ , x + ϵ)', indicating synthetic data generation rather than the use of a publicly available dataset with concrete access information.
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, or detailed splitting methodology) for training, validation, or testing. It mentions 'The sample size n varies from 200 to 1000' but not how this data is split.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details, such as library or solver names with version numbers, needed to replicate the experiments.
Experiment Setup Yes In the experiment, we focus on model (3) with sparse θ . The problem dimension is fixed as p = 1000, and the sparsity of θ is set to 10. Essentially we generate our data (x, y) from y = f ( θ , x + ϵ) , where x N(0, I) and ϵ N(0, σ2). σ ranges from 0.3 to 1.5. We choose three monotonically increasing f, f(z) = 1/(1 + exp( z)) (which is bounded and Lipschitz), f(z) = z3 (which is unbounded and non-Lipschitz), and f(z) = log(1 + exp(z)) (which is unbounded but Lipschitz). The sample size n varies from 200 to 1000. We use the estimator (23) in Section 3. ... The number of its iterations is fixed to 100. The best tuning parameter of i SILO is obtained by grid search.