Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Trimmed Maximum Likelihood Estimation for Robust Generalized Linear Model
Authors: Pranjal Awasthi, Abhimanyu Das, Weihao Kong, Rajat Sen
NeurIPS 2022 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | Our key theoretical contribution in this work is a general analysis of the trimmed MLE estimator. In particular, we show that for a broad family of GLMs, and under adversarial corruptions of only the labels, not only does the iterative trimmed MLE estimator enjoy theoretical guarantees, it in fact nearly achieves the minimax error rate! |
| Researcher Affiliation | Industry | Pranjal Awasthi Google Research EMAIL Abhimanyu Das Google Research EMAIL Weihao Kong Google Research EMAIL Rajat Sen Google Research EMAIL |
| Pseudocode | Yes | Algorithm 1: Alternating minimization of trimmed maximum likelihood estimator |
| Open Source Code | No | Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [N/A] |
| Open Datasets | No | The paper is theoretical and does not mention specific datasets (like MNIST or CIFAR-10), nor does it provide any links, DOIs, or citations for specific data used for training or empirical evaluation. The ethics checklist confirms N/A for experiments and data. |
| Dataset Splits | No | The paper is theoretical and does not conduct empirical experiments, hence it does not specify any training, validation, or test dataset splits. |
| Hardware Specification | No | The paper states '[N/A]' for the question 'Did you include the total amount of compute and the type of resources used (e.g., type of GPUs, internal cluster, or cloud provider)?', indicating no hardware specifications were provided for running experiments. |
| Software Dependencies | No | The paper is theoretical and does not mention specific software dependencies with version numbers (e.g., libraries, frameworks, or solvers) required to reproduce experimental results. |
| Experiment Setup | No | The paper focuses on theoretical analysis and algorithm design. It explicitly states '[N/A]' for 'training details (e.g., data splits, hyperparameters, how they were chosen)', indicating no specific experimental setup details were provided. |