Robust Conditional Probabilities

Authors: Yoav Wald, Amir Globerson

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

Reproducibility Variable Result LLM Response
Research Type Experimental We apply them to semi-supervised deep learning, obtaining results competitive with variational autoencoders. (Abstract) 6 Experiments To evaluate the utility of our bounds, we consider their use in settings of semi-supervised deep learning and structured prediction. (Section 6) We trained the above models on the MNIST dataset, using 100 and 1000 labeled samples (Section 6.2) Results are shown in Figure 1. (Section 6.2)
Researcher Affiliation Academia Yoav Wald School of Computer Science and Engineering Hebrew University yoav.wald@mail.huji.ac.il Amir Globerson The Balvatnik School of Computer Science Tel-Aviv University gamir@mail.tau.ac.il
Pseudocode No The paper describes mathematical derivations and algorithms in text, but it does not include structured pseudocode or algorithm blocks.
Open Source Code No The paper does not contain an explicit statement about releasing open-source code for the methodology described.
Open Datasets Yes We trained the above models on the MNIST dataset, using 100 and 1000 labeled samples (see [11] for a similar setup). (Section 6.2) and The Genbase dataset taken from [26], is a protein classification multilabel dataset. (Section 6.3)
Dataset Splits Yes We used 10% of the training data as a validation set and compared error rates on the 10^4 samples of the test set.
Hardware Specification No The paper does not provide specific hardware details (like exact GPU/CPU models or memory amounts) used for running its experiments.
Software Dependencies No The paper mentions software components like 'multilayer perceptron (MLP)' and 'pystruct' but does not specify their version numbers or other software dependencies with concrete version details.
Experiment Setup No The paper describes the neural network architecture (e.g., 'hidden layers of sizes 1000, 500, 50') and regularization techniques used ('ℓ2 regularization'), but it does not provide specific hyperparameter values like learning rates, batch sizes, or the actual values of regularization parameters.