List-Decodable Sparse Mean Estimation

Authors: Shiwei Zeng, Jie Shen

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Our main contribution is the first polynomial-time algorithm that enjoys sample complexity O poly(k, log d) , i.e. poly-logarithmic in the dimension. One of our core algorithmic ingredients is using low-degree sparse polynomials to filter outliers, which may find more applications. [N/A] Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)?
Researcher Affiliation Academia Shiwei Zeng Department of Computer Science Stevens Institute of Technology szeng4@stevens.edu Jie Shen Department of Computer Science Stevens Institute of Technology jie.shen@stevens.edu
Pseudocode Yes Algorithm 1 CLUSTER(T, , , ), Algorithm 2 Main Algorithm: Attribute-Efficient List-Decodable Mean Estimation, Algorithm 3 ATTRIBUTE-EFFICIENT-MULTIFILTER(T, , , ), Algorithm 4 BASICMF(T, , , p), Algorithm 5 HARMONICMF(T, , , p)
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 focuses on theoretical analysis using a 'set T of samples' generated from a Gaussian distribution for its proofs (e.g., Theorem 1), rather than using or providing access to concrete, publicly available datasets for empirical training. The ethics review guidelines also state N/A for data-related questions implying no external datasets were used/released for experiments.
Dataset Splits No The paper is theoretical and does not describe empirical experiments with data splits. The ethics review guidelines state '[N/A]' for 'Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)?'.
Hardware Specification No The paper focuses on theoretical algorithms and does not describe empirical experiments or specific hardware used. The ethics review guidelines state '[N/A]' for 'Did you include the total amount of compute and the type of resources used (e.g., type of GPUs, internal cluster, or cloud provider)?'.
Software Dependencies No The paper describes algorithms but does not provide specific software dependencies or version numbers, as it is a theoretical work without empirical implementation details. The ethics review guidelines state '[N/A]' for experimental results.
Experiment Setup No The paper is theoretical and focuses on algorithm design and proofs, rather than empirical experiments. Consequently, it does not describe an experimental setup with hyperparameters or training details. The ethics review guidelines state '[N/A]' for 'Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)?'.