Europe
MetaInit: Initializing learning by learning to initialize
Yann N. Dauphin, Samuel Schoenholz
Neural Information Processing Systems http://nips.cc/
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.
Learning Hawkes Processes from a handful of events
Farnood Salehi, William Trouleau, Matthias Grossglauser, Patrick Thiran
Neural Information Processing Systems http://nips.cc/
Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel
Colin Wei, Jason D. Lee, Qiang Liu, Tengyu Ma
Recent works have shown that on sufficiently over-parametrized neural nets, gradient descent with relatively large initialization optimizes a prediction function in the RKHS of the Neural Tangent Kernel (NTK).
Single-Agent Policy Tree Search With Guarantees
Laurent Orseau, Levi Lelis, Tor Lattimore, Theophane Weber
Neural Information Processing Systems http://nips.cc/
SCRREAM: SCan, Register, REnder And Map: A Framework for Annotating Accurate and Dense 3D Indoor Scenes with a Benchmark
Indoor tasks are heavily related to human activities.
