Country
Imitation-Projected Programmatic Reinforcement Learning
Abhinav Verma, Hoang Le, Yisong Yue, Swarat Chaudhuri
Neural Information Processing Systems http://nips.cc/
Provably Correct Automatic Sub-Differentiation for Qualified Programs
Neural Information Processing Systems http://nips.cc/
and
Successfully employing cutting planes can be challenging because there are infinitely many cuts to choose from and there are still many open questions about which cuts to employ when.
Learning a High Fidelity Pose Invariant Model for High-resolution Face Frontalization
Jie Cao, Yibo Hu, Hongwen Zhang, Ran He, Zhenan Sun
Neural Information Processing Systems http://nips.cc/
Explicitly disentangling image content from translation and rotation with spatial-VAE
Tristan Bepler, Ellen Zhong, Kotaro Kelley, Edward Brignole, Bonnie Berger
Neural Information Processing Systems http://nips.cc/
ComputationalMirrors: BlindInverseLight TransportbyDeepMatrixFactorization
Matrix factorization is known to be very ill-posed. Factorizations for any matrix are in principle easy to find: we can simply choose one of the factors at will (as afull-rank matrix) and recover a compatible factor by pseudoinversion.
Which Neural Net Architectures Give Rise to Exploding and Vanishing Gradients?
In this article, we continue this line of investigation.