Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
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.
Efficient List-Decodable Regression using Batches
Authors: Abhimanyu Das, Ayush Jain, Weihao Kong, Rajat Sen
ICML 2023 | Venue PDF | LLM Run Details | Input Tokens: 45,863 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 3,355 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We demonstrate the use of batches in studying list-decodable linear regression, in which only α (0, 1] fraction of batches contain genuine samples from a common distribution and the rest can contain arbitrary or even adversarial samples. When genuine batches have Ω(1/α) samples each, our algorithm can efficiently find a small list of potential regression parameters, with a high probability that one of them is close to the true parameter. This is the first polynomial time algorithm for list-decodable linear regression, and its sample complexity scales nearly linearly with the dimension of the covariates. |
| Researcher Affiliation | Collaboration | 1Google Research 2UC San Diego. The majority of this work was completed while Ayush Jain was an intern at Google Research. Correspondence to: Ayush Jain <EMAIL>. |
| Pseudocode | Yes | Algorithm 1 MAINALGORITHM 1: Input: Data {{(xb i, yb i )}i [n]}b B, α, C, σ. 2: For each b B, βb init 1 and βinit {βb init}b B. 3: List L {βinit} and M . 4: while L = do 5: Pick any element β in L and remove it from L. [...] Algorithm 2 FINDCLIPPINGPPARAMETER 1: Input: Set B, β, σ, a1 1, a2 data {{(xb i, yb i }i [n]}b B. 2: κ 3: while True do 4: wκ any approximate stationary point of clipped losses {f b( , κ)} w.r.t. weight vector β such that Eβ[f b(wκ, κ)] log(2/α)σ |
| Open Source Code | No | The paper does not provide any statements about releasing code, nor does it include links to a code repository. |
| Open Datasets | No | The paper is theoretical and does not use or reference any specific public or open datasets for training. |
| Dataset Splits | No | The paper is theoretical and does not describe empirical experiments involving dataset splits (e.g., training, validation, test splits). |
| Hardware Specification | No | The paper is theoretical and does not describe empirical experiments; therefore, no hardware specifications are mentioned. |
| Software Dependencies | No | The paper does not mention any specific software dependencies or version numbers needed to replicate the work. |
| Experiment Setup | No | The paper is theoretical and focuses on algorithm design and proofs. It does not describe any experimental setup details such as hyperparameters or system-level training settings. |