Stochastic Optimization Algorithms for Instrumental Variable Regression with Streaming Data

Authors: Xuxing Chen, Abhishek Roy, Yifan Hu, Krishnakumar Balasubramanian

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

Reproducibility Variable Result LLM Response
Research Type Experimental Numerical experiments are provided to corroborate the theoretical results.
Researcher Affiliation Academia Xuxing Chen Department of Mathematics University of California, Davis xuxchen@ucdavis.edu Abhishek Roy Halıcıo glu Data Science Institute University of California, San Diego a2roy@ucsd.edu Yifan Hu College of Management, EPFL Department of Computer Science, ETH Zurich yifan.hu@epfl.ch Krishnakumar Balasubramanian Department of Statistics University of California, Davis kbala@ucdavis.edu
Pseudocode Yes Algorithm 1 Two-sample One-stage Stochastic Gradient-IVa R (TOSG-IVa R) Input: of iterations T, stepsizes {αt}T t=1, initial iterate θ1.
Open Source Code Yes We also provide the code in the main supplemental material.
Open Datasets Yes We further conduct experiments on real-world datasets provided in [AE96] and [Rya12].
Dataset Splits No The paper describes training data generation and test samples but does not explicitly mention or describe a separate validation split for hyperparameter tuning or model selection.
Hardware Specification Yes All experiments in Section 4 were conducted on a computer with an 11th Intel(R) Core(TM) i711370H CPU.
Software Dependencies No The paper mentions the CPU used for experiments but does not specify any software dependencies (e.g., libraries, frameworks) with version numbers.
Experiment Setup Yes We set (dx, dz) {(4, 8), (8, 16)}, c {0.1, 1.0}, and ϕ(s) {s, s2}. [...] set αt α = log T /µT [...] αt = Cαt 1+ι/2 and βt = Cβt 1+ι/2