![4. Beyond Gradient Descent - Fundamentals of Deep Learning [Book]](https://www.oreilly.com/api/v2/epubs/9781491925607/files/assets/fodl_0405.png "4. Beyond Gradient Descent - Fundamentals of Deep Learning [Book]")
4. Beyond Gradient Descent - Fundamentals of Deep Learning [Book]
Escaping from Saddle Points – Off the convex path
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
Escaping from Saddle Points – Off the convex path
Gradient Descent in Machine Learning - Javatpoint
Gradient Descent converging to a Saddle Point | Beni Bogoşel's blog
Figure 2 from Identifying and attacking the saddle point problem in high-dimensional non-convex optimization | Semantic Scholar
Momentum-based Gradient Descent: Adaptive Optimization in Machine Learning
optimization - Oscillating around the saddle point in gradient descent? - Artificial Intelligence Stack Exchange
How to Escape Saddle Points Efficiently – The Berkeley Artificial Intelligence Research Blog
Gabriel Peyré on X: "Gradient descent is inefficient to find saddle point (Nash equilibrium) for min-max games, because of spiralling behaviour. Beware when training your GANs … https://t.co/KKKGQ4q9JA https://t.co/xjgLuUHPMU https://t.co/hYYH0xWUXP" / X
Intro to optimization in deep learning: Gradient Descent
Gradient Descent converging to a Saddle Point | Beni Bogoşel's blog
Intro to optimization in deep learning: Gradient Descent
Figure 2 from Gradient Descent Can Take Exponential Time to Escape Saddle Points | Semantic Scholar
The journey of Gradient Descent — From Local to Global | by Pradyumna Yadav | Analytics Vidhya | Medium
What is Gradient Descent? | IBM
David Li-Bland's Blog - Saddle Points and Stochastic Gradient Descent
How to Escape Saddle Points Efficiently – The Berkeley Artificial Intelligence Research Blog
Frontiers | Noise Helps Optimization Escape From Saddle Points in the Synaptic Plasticity
David Li-Bland's Blog - Saddle Points and Stochastic Gradient Descent
Momentum-Based Gradient Descent - Scaler Topics
Efficient approaches for escaping higher order saddle points in non-convex optimization - YouTube
Escaping from Saddle Points – Off the convex path
