Adaptive Passive-Aggressive Framework for Online Regression with Side Information

Authors: Runhao Shi, Jiaxi Ying, Daniel Palomar

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Numerical experiments show that our model achieves outstanding performance associated with the side information while maintaining low tracking error, demonstrating marked improvements over traditional PA methods across various scenarios.
Researcher Affiliation Academia Runhao Shi, Jiaxi Ying, Daniel P. Palomar The Hong Kong University of Science and Technology {rshiaf, jx.ying}@connect.ust.hk, palomar@ust.hk
Pseudocode Yes Algorithm 1 Adaptive Passive-Aggressive Framework with Side Information (APAS)
Open Source Code Yes Does the paper provide open access to the data and code, with sufficient instructions to faithfully reproduce the main experimental results, as described in supplemental material? Answer: [Yes] , Justification: The code, data, and instructions to reproduce the experiments are available in the supplemental material.
Open Datasets No We conduct simulations on two well-known indices using real market data from Yahoo! Finance TM: the S&P 500 Index and the NASDAQ 100 Index. For the S&P 500 Index, we collect data from 2021-01-01 to 2023-01-01... For the NASDAQ 100 Index, we collect data from 2019-01-01 to 2021-01-01... The paper mentions using data from 'Yahoo! Finance TM' but does not provide a specific link, DOI, or formal citation for the collected dataset.
Dataset Splits No The training set consists of 50% of the data, while the test set contains the remaining 50%. The paper specifies training and test splits but does not explicitly mention a validation set split or methodology for it.
Hardware Specification Yes The experiments are conducted on a PC equipped with a 13th Gen Intel(R) Core(TM) i7-13700 CPU and 16GB of memory.
Software Dependencies No The paper mentions software like CVXR, PGD, and ADMM but does not provide specific version numbers for these or any other software dependencies.
Experiment Setup Yes The training set consists of 50% of the data, while the test set contains the remaining 50%. Both SLAIT-ETE and SLAIT-DR use a rolling training window of 100-day observations, rebalanced every 3 days.