Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP

Authors: Satyen Kale, Zohar Karnin, Tengyuan Liang, Dávid Pál

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

Reproducibility Variable Result LLM Response
Research Type Theoretical We design polynomial-time algorithms for online sparse linear regression for two models for the sequence (x1, y1), (x2, y2), . . . , (x T , y T ). The algorithm for the agnostic setting relies on the theory of submodular optimization. The main result in this section provides a logarithmic regret bound under the following assumptions
Researcher Affiliation Collaboration 1Google Research, New York. 2Amazon, New York. 3University of Chicago, Booth School of Business, Chicago. 4Yahoo Research, New York.
Pseudocode Yes Algorithm 1 Dantzig Selector for POSLR
Open Source Code No The paper does not contain any statement about releasing source code or a link to a code repository for the described methodology.
Open Datasets No This is a theoretical paper that defines abstract sequences of data (x1, y1), (x2, y2), ..., (xT, yT) and does not specify or use any publicly available datasets for empirical training or evaluation.
Dataset Splits No This is a theoretical paper and does not describe experiments that involve training, validation, or test data splits.
Hardware Specification No This is a theoretical paper focusing on algorithm design and analysis; it does not mention any specific hardware used for running experiments.
Software Dependencies No The paper describes algorithms and their theoretical properties but does not mention specific software dependencies with version numbers required for replication.
Experiment Setup No This is a theoretical paper and does not include details about an experimental setup, hyperparameters, or training configurations.