Spotlight Talk: How to Escape Saddle Points Efficiently - YouTube
Gradient descent - Wikipedia
Intro to optimization in deep learning: Gradient Descent
Gradient Descent converging to a Saddle Point | Beni Bogoşel's blog
Stabilizing GANs with Prediction
How to Escape Saddle Points Efficiently – The Berkeley Artificial Intelligence Research Blog
Trajectory for gradient descent algorithms with red and black arrows on... | Download Scientific Diagram
DL] 4. More about Gradient Descent and Activation Functions | by jun94 | jun-devpBlog | Medium
Escaping from Saddle Points – Off the convex path
optimization - Oscillating around the saddle point in gradient descent? - Artificial Intelligence Stack Exchange
multivariable calculus - Confused about how the gradient represents direction of maximum rate of increase - Mathematics Stack Exchange
Escaping from Saddle Points – Off the convex path
Gradient Ascent #8 - by Albert Azout - Gradient Ascent
Damek Davis on X: "Gradient descent doesn't avoid saddle points of C^1 smooth functions. Random initialization doesn't help. If you start in the crevice, you stay in the crevice. You need C^2
Intro to optimization in deep learning: Gradient Descent
Pitfalls of gradient descent - Hyperskill
4. Beyond Gradient Descent - Fundamentals of Deep Learning [Book]
gradient descent - How can it be trapped in a saddle point? - Cross Validated
Saddle point in deep neural network | Download Scientific Diagram
Creating a Gradient Descent Animation in Python | by Luis Medina | Nov, 2023 | Towards Data Science
KiKaBeN - Gradient Descent Optimizers
How to Escape Saddle Points Efficiently – The Berkeley Artificial Intelligence Research Blog
How to Escape Saddle Points Efficiently – The Berkeley Artificial Intelligence Research Blog
David Li-Bland's Blog - Saddle Points and Stochastic Gradient Descent
Efficient approaches for escaping higher order saddle points in non-convex optimization - YouTube
David Li-Bland's Blog - Saddle Points and Stochastic Gradient Descent