Adaptive Dropout Rates for Learning with Corrupted Features

Authors: Jingwei Zhuo, Jun Zhu, Bo Zhang

IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical results on various datasets demonstrate the effectiveness on avoiding extensive tuning and sometimes improving the performance due to its flexibility.
Researcher Affiliation Academia Jingwei Zhuo, Jun Zhu, Bo Zhang Dept. of Comp. Sci. & Tech., State Key Lab of Intell. Tech. & Sys., TNList Lab, Center for Bio-Inspired Computing Research, Tsinghua University, Beijing, 100084, China Jiangsu Collaborative Innovation Center for Language Ability, Xuzhou, 221009, China zhuojw10@mails.tsinghua.edu.cn, dcszj@tsinghua.edu.cn, dcszb@tsinghua.edu.cn
Pseudocode No The paper describes the algorithm steps in paragraph text (e.g., 'our algorithm iteratively performs the following steps: For η: update... For q(λ): infer... For θ: plug...'), but does not provide structured pseudocode or an algorithm block.
Open Source Code No The paper does not provide any specific links or explicit statements about the release of its source code.
Open Datasets Yes The Amazon review datasets... [Blitzer et al., 2007]; The MEMset Donor dataset... Available at: http://genes.mit.edu/burgelab/maxent/ssdata/; 20 Newsgroup dataset... Available at: http://people.csail.nut.edu/jrennie/20Newsgroups/; MNIST dataset... Available at: http://yann.lecun.com/exdb/mnist/
Dataset Splits Yes Here we follow the setup in [Meier et al., 2008], which splits the original training set into a balanced training set (5,610 true and 5,610 false instances) and an unbalanced validation set (2,805 true and 59,804 false instances) which has the same true/false ratio as the testing set.
Hardware Specification No The paper mentions 'a single thread' in the context of training time, but does not provide any specific hardware details like GPU/CPU models, processor types, or memory amounts used for the experiments.
Software Dependencies No The paper mentions implementation 'in C++ using L-BFGS methods', but no specific version numbers for the programming language, compiler, or any libraries/solvers are provided.
Experiment Setup Yes We run the algorithms with 640 iterations, which are sufficiently large for all methods to converge. We adopt the one-vs-all strategy [Rifkin and Klautau, 2004]... we set different weights for the contribution of the positive and negative instances in Eq. (15) corresponding to the ratio r of numbers between the positive and negative instances to make a balance