Variational inference & deep learning: A new synthesis
By Diederik P. Kingma. 2017
68 citations recorded by the source corpus.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
Citations in the corpus
- End-to-end protein–ligand complex structure generation with diffusion-based generative models (2022, background): “Deep generative modeling [21, 22] is a powerful approach to model high-dimensional and multimodal data distributions and generate samples efficiently.”
- Lifelong Generative Modeling (2017, methodology): “Very often the marginal likelihood P θ ( x ) will be intractable because the integral in equation (1) does not have an analytical form nor an efficient estimator Kingma (2017).”
- A Generative Model for Sampling High-Performance and Diverse Weights for Neural Networks (2019, methodology): “, 2017; Louizos & Welling, 2017) are set up in a Bayesian context, require a probabilistic interpretation of the target neural network’s output, and harness Variational Inference (VI) (Hinton & Van Camp, 1993; Graves, 2011; Kingma, 2017) to approximate the posterior of the weights given the data and”
- Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network (2018, background): “, 2005) or Gaussian mixture, although in these cases the KL-divergence of prior and posterior is hard to compute and practically we replace it with the Monte-Carlo estimator, which has higher variance, resulting in slower convergence rate (Kingma, 2017).”