Functional Gradient Boosting based on Residual Network Perception

Authors: Atsushi Nitanda, Taiji Suzuki

ICML 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results show superior performance of the proposed method over state-of-the-art methods such as Light GBM.
Researcher Affiliation Academia 1Graduate School of Information Science and Technology, The University of Tokyo 2Center for Advanced Intelligence Project, RIKEN.
Pseudocode Yes Algorithm 1 Res FGB [...] Algorithm 2 Sample-splitting Res FGB
Open Source Code No The paper does not provide any statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets Yes We use the following benchmark datasets: letter, usps, ijcnn1, mnist, covtype, and susy.
Dataset Splits Yes For datasets not providing a fixed test set, we first divide each dataset randomly into two parts: 80% for training and the rest for test. We next divide each training set randomly and use 80% for training and the rest for validation.
Hardware Specification No The paper does not provide specific details about the hardware used for experiments.
Software Dependencies No The paper mentions using a
Experiment Setup Yes The number of hidden units in each layer is set to 100 or 1000. Linear classifiers and embeddings are trained by Nesterov s momentum method. The learning rate is chosen from {10 3, 10 2, 10 1, 1}. These parameters and the number of iterations T are tuned based on the performance on the validation set.