Country
Deep ReLU Networks Have Surprisingly Few Activation Patterns
Neural Information Processing Systems http://nips.cc/
RenderNet: A deep convolutional network for differentiable rendering from 3D shapes
Thu H. Nguyen-Phuoc, Chuan Li, Stephen Balaban, Yongliang Yang
Neural Information Processing Systems http://nips.cc/
ASPiRe: AdaptiveSkillPriorsforReinforcementLearning
Transferring prior experience to new tasks is central to an agent's adaptability. In this work, we aim to accelerate online reinforcement learning by leveraging prior experience from large offline data.
Gradient-FreeMethodsforNonconvexNonsmooth StochasticCompositionalOptimization
Most of the existing work [2, 5, 6, 7, 8] for nonconvex SCO problem is based on the assumption that both functionsf()andg()are smooth.
Algorithmic Linearly Constrained Gaussian Processes
Neural Information Processing Systems http://nips.cc/
DINGO: Distributed Newton-Type Method for Gradient-Norm Optimization
Neural Information Processing Systems http://nips.cc/
Fast-rate PAC-Bayes Generalization Bounds via Shifted Rademacher Processes
Jun Yang, Shengyang Sun, Daniel M. Roy
The developments of Rademacher complexity and PAC-Bayesian theory have been largely independent.