Large Margin Deep Networks for Classification

Authors: Gamaleldin Elsayed, Dilip Krishnan, Hossein Mobahi, Kevin Regan, Samy Bengio

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

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate that the decision boundary obtained by our loss has nice properties compared to standard classification loss functions. Specifically, we show improved empirical results on the MNIST, CIFAR-10 and Image Net datasets on multiple tasks: generalization from small training sets, corrupted labels, and robustness against adversarial perturbations.
Researcher Affiliation Industry Gamaleldin F. Elsayed Google Research Dilip Krishnan Google Research Hossein Mobahi Google Research Kevin Regan Google Research Samy Bengio Google Research
Pseudocode No The paper presents mathematical formulations but does not include any structured pseudocode or algorithm blocks.
Open Source Code Yes Code for the large margin loss function is released at https://github.com/google-research/ google-research/tree/master/large_margin
Open Datasets Yes Specifically, we show improved empirical results on the MNIST, CIFAR-10 and Image Net datasets on multiple tasks
Dataset Splits Yes We hold out 5, 000 samples of the training set as a validation set, and the remaining 55, 000 samples are used for training.
Hardware Specification Yes measured on the same NVIDIA p100 GPU
Software Dependencies No Our code was written in Tensorflow (Abadi et al., 2016). (No version number provided for TensorFlow or other software components.)
Experiment Setup Yes We train a 4 hidden-layer model with 2 convolutional layers and 2 fully connected layers, with rectified linear unit (Re Lu) activation functions, and a softmax output layer. The first baseline model uses a cross-entropy loss function, trained with stochastic gradient descent optimization with momentum and learning rate decay.