Deep Learning
Generalized Eigenvalue Problems with Generative Priors
Generalized eigenvalue problems (GEPs) find applications in various fields of science and engineering. For example, principal component analysis, Fisher's discriminant analysis, and canonical correlation analysis are specific instances of GEPs and are widely used in statistical data processing. In this work, we study GEPs under generative priors, assuming that the underlying leading generalized eigenvector lies within the range of a Lipschitz continuous generative model.
Latent Field Discovery In Interacting Dynamical Systems With Neural Fields
Systems of interacting objects often evolve under the influence of field effects that govern their dynamics, yet previous works have abstracted away from such effects, and assume that systems evolve in a vacuum. In this work, we focus on discovering these fields, and infer them from the observed dynamics alone, without directly observing them.
MetaInit: Initializing learning by learning to initialize
Yann N. Dauphin, Samuel Schoenholz
Neural Information Processing Systems http://nips.cc/
Joint Autoregressive and Hierarchical Priors for Learned Image Compression
David Minnen, Johannes Ballé, George D. Toderici
Inspired by the success of autoregressive priors in probabilistic generative models,weexamineautoregressive,hierarchical, andcombined priorsasalternatives, weighing their costs and benefits in the context of image compression.
First, we derive a well-behaved regularized relativistic GAN loss that addresses issues of mode dropping and non-convergence that were previously tackled via a
There is a widely-spread claim that GANs are difficult to train, and GAN architectures in the literature are littered with empirical tricks.
Single-Agent Policy Tree Search With Guarantees
Laurent Orseau, Levi Lelis, Tor Lattimore, Theophane Weber
Neural Information Processing Systems http://nips.cc/
Regularizing by the Variance of the Activations' Sample-Variances
Neural Information Processing Systems http://nips.cc/
Multiple Futures Prediction
Charlie Tang, Russ R. Salakhutdinov
Neural Information Processing Systems http://nips.cc/