Hierarchical Implicit Models and Likelihood-Free Variational Inference

By Dustin Tran, Rajesh Ranganath, David M. Blei. 2017

245 citations recorded by the source corpus.

Subfields: Probabilistic & Bayesian Methods

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Probabilistic & Bayesian Methods

Citations in the corpus

Large Scale GAN Training for High Fidelity Natural Image Synthesis (2018, methodology): “(2018), which uses the hinge loss (Lim & Ye, 2017; Tran et al., 2017) GAN objective.”
Spectral Normalization for Generative Adversarial Networks (2018, methodology): “This type of loss has been already proposed and used in Lim & Ye (2017); Tran et al. (2017).”
Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis (2020, methodology): “For the discriminator, we utilize the hinge version [27], [28] of the standard adversarial loss [1],”
Cross-Modal Contrastive Learning for Text-to-Image Generation (2021, background): “A large amount of work has focused on designing the adversarial objective to improve training [12, 1, 31, 47, 29, 54].”
cGANs with Projection Discriminator (2018, methodology): “For the objective function, we used the following hinge version of the standard adversarial loss (1) (Lim & Ye, 2017; Tran et al., 2017) where the last activation function A of D is identity function. p ( z ) is standard Gaussian distribution and G ( z , y ) is the generator network.”
End-to-End Adversarial Text-to-Speech (2020, positive): “The loss function we use to train the generator is as follows: where L G, adv is the adversarial loss, linear in the discriminators’ outputs, paired with the hinge loss [35, 57] used as the discriminators’ objective, as used in GAN-TTS [8].”
Consistency Regularization for Generative Adversarial Networks (2019, methodology): “Speciﬁcally, we evaluate regularization methods using three loss functions: the non-saturating loss (NS) (Goodfellow et al., 2014), the Wasserstein loss (WAS) (Arjovsky et al., 2017), and the hinge loss (Hinge) (Lim & Ye, 2017; Tran et al., 2017).”
Sliced Score Matching: A Scalable Approach to Density and Score Estimation (2019, background): “Implicit distributions can arise in many more situations such as the marginal distribution of a non-conjugate model (Sun et al., 2019), and models deﬁned by complex simulation processes (Tran et al., 2017).”
Discriminator Rejection Sampling (2018, methodology): “Finally, this whole model is trained using a special hinge version of the adversarial loss (Lim & Ye, 2017; Miyato & Koyama, 2018; Tran et al., 2017): (2)”
LOGAN: Latent Optimisation for Generative Adversarial Networks (2019, methodology): “Our experiments with BigGANdeep use the hinge loss (Lim & Ye, 2017; Tran et al., 2017), which is identical to this form in its linear regime.”
Improving MMD-GAN Training with Repulsive Loss Function (2018, methodology): “md G ) using Gaussian kernel (MMD-rbf) (Li et al. (2017a)) and rational quadratic kernel (MMD-rq) (Binkowski et al. (2018)), as well as non-saturating loss (Goodfellow et al. (2014)) and´ hinge loss (Tran et al. (2017)). To show the efﬁcacy of RBF-B kernel, we applied it to both Latt D and Lrep D , ”
X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers (2020, methodology): “Our generator and discrminator are trained with 4 losses: (1) hinge adversarial loss (Lim and Ye, 2017; Tran et al., 2017), (2) AC-GAN loss (Odena et al., 2017), (3) discriminator feature match loss (Wang et al., 2018) and (4) perceptual loss (Johnson et al., 2016) following (Park et al., 2019).”
Implicit Causal Models for Genome-wide Association Studies (2017, unknown): “Implicit models capture an unknown distribution by hypothesizing about its generative process [4, 24].”