Robustness Guarantees for Mode Estimation with an Application to Bandits
Authors: Aldo Pacchiano, Heinrich Jiang, Michael I. Jordan9277-9284
AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We show in simulations that our algorithms are robust to perturbation of the arms by adversarial noise sequences, thus rendering modal bandits an attractive choice in situations where the rewards may have outliers or adversarial corruptions. ... In Figure 2, we test the robustness of Algorithm 3 to perturbations of the arms. |
| Researcher Affiliation | Collaboration | Aldo Pacchiano,1 Heinrich Jiang,2 Michael I. Jordan1 1UC Berkeley 2Google Research pacchiano@berkeley.edu, heinrichj@google.com, jordan@cs.berkeley.edu |
| Pseudocode | Yes | Algorithm 1 Estimating the mode... Algorithm 2 Differentially Private Mode Estimation... Algorithm 3 UCB Strategy... Algorithm 4 Uniform Sampling Strategy |
| Open Source Code | No | The paper does not include an unambiguous statement or a direct link indicating that the source code for the described methodology is available. A footnote links to the full paper on arXiv, not a code repository. |
| Open Datasets | Yes | We also include some results regarding the robustness of our algorithms under random removals on the Open ML benchmark datasets. The methodology and results are described in Tables 1 and 2. |
| Dataset Splits | No | The paper uses 'Open ML benchmark datasets' and implicitly refers to 'training set' ('variance for that coordinate in the training set' in Table 2), but it does not specify explicit train/validation/test splits (e.g., percentages or sample counts) for reproducibility. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory, or cloud instance types) 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 experiment. |
| Experiment Setup | Yes | For each of the datasets, we use k = 100 for the mode estimation... We average over 25 random seeds... Algorithm 1 Input: k and sample points X = {X1, ..., Xn}. ... Algorithm 3 Input: Total time n and confidence parameter δ. |