Adversarially Learned Inference

Authors: Vincent Dumoulin, Ishmael Belghazi, Ben Poole, Alex Lamb, Martin Arjovsky, Olivier Mastropietro, Aaron Courville

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

Reproducibility Variable Result LLM Response
Research Type Experimental With experiments on the Street View House Numbers (SVHN) dataset (Netzer et al., 2011), the CIFAR-10 object recognition dataset (Krizhevsky & Hinton, 2009), the Celeb A face dataset (Liu et al., 2015) and a downsampled version of the Image Net dataset (Russakovsky et al., 2015), we show qualitatively that we maintain the high sample fidelity associated with the GAN framework, while gaining the ability to perform efficient inference. We show that the learned representation is useful for auxiliary tasks by achieving results competitive with the state-of-the-art on the semi-supervised SVHN and CIFAR10 tasks.
Researcher Affiliation Academia 1 MILA, Université de Montréal, firstname.lastname@umontreal.ca. 2 Neural Dynamics and Computation Lab, Stanford, poole@cs.stanford.edu. 3 New York University, martinarjovsky@gmail.com.
Pseudocode Yes Algorithm 1 The ALI training procedure.
Open Source Code Yes The code for all experiments can be found at https://github.com/IshmaelBelghazi/ALI.
Open Datasets Yes With experiments on the Street View House Numbers (SVHN) dataset (Netzer et al., 2011), the CIFAR-10 object recognition dataset (Krizhevsky & Hinton, 2009), the Celeb A face dataset (Liu et al., 2015) and a downsampled version of the Image Net dataset (Russakovsky et al., 2015).
Dataset Splits Yes A 10,000 example held-out validation set is taken from the training set and is used for model selection.
Hardware Specification No The paper does not specify any particular hardware used for experiments, such as GPU models, CPU types, or cloud computing instances with detailed specifications.
Software Dependencies Yes We would also like to thank the developers of Theano (Bergstra et al., 2010; Bastien et al., 2012; Theano Development Team, 2016), Blocks and Fuel (van Merriënboer et al., 2015).
Experiment Setup Yes A HYPERPARAMETERS ... Table 3: CIFAR10 model hyperparameters (unsupervised). ... Optimizer Adam (α = 10 4, β1 = 0.5, β2 = 10 3) Batch size 100 Epochs 6475 Leaky Re LU slope, maxout pieces 0.1, 2 Weight, bias initialization Isotropic gaussian (µ = 0, σ = 0.01), Constant(0)