NIPS Proceedingsβ

Simon S. Du

11 Papers

  • Acceleration via Symplectic Discretization of High-Resolution Differential Equations (2019)
  • Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels (2019)
  • On Exact Computation with an Infinitely Wide Neural Net (2019)
  • Provably Efficient Q-learning with Function Approximation via Distribution Shift Error Checking Oracle (2019)
  • Towards Understanding the Importance of Shortcut Connections in Residual Networks (2019)
  • Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced (2018)
  • How Many Samples are Needed to Estimate a Convolutional Neural Network? (2018)
  • Gradient Descent Can Take Exponential Time to Escape Saddle Points (2017)
  • Hypothesis Transfer Learning via Transformation Functions (2017)
  • On the Power of Truncated SVD for General High-rank Matrix Estimation Problems (2017)
  • Efficient Nonparametric Smoothness Estimation (2016)