Gradient flow in parameter space is equivalent to linear interpolation in output space

Similar Items

• Interpretable global minima of deep ReLU neural networks on sequentially separable data
  by: Chen, Thomas, et al.
  Published: (2024)
• On non-approximability of zero loss global ${\mathcal L}^2$ minimizers by gradient descent in Deep Learning
  by: Chen, Thomas, et al.
  Published: (2023)
• Geometric structure of shallow neural networks and constructive ${\mathcal L}^2$ cost minimization
  by: Chen, Thomas, et al.
  Published: (2023)
• Geometric structure of Deep Learning networks and construction of global ${\mathcal L}^2$ minimizers
  by: Chen, Thomas, et al.
  Published: (2023)
• Global $\mathcal{L}^2$ minimization at uniform exponential rate via geometrically adapted gradient descent in Deep Learning
  by: Chen, Thomas
  Published: (2023)