Gradient descent - Wikipedia

Gabriel Peyré on X: Gradient descent/ascent can be inefficient to find saddle point (Nash equilibrium) for min-max games, because of spiralling behaviour. / X

A Simple Guide to Gradient Descent Algorithm, by Data Science Wizards

Gabriel Peyré on X: Comparison of explicit vs implicit descent to minimize a function. Explicit l1 is equivalent to a coordinate descent, and L2 is the usual gradient descent. /

Part 1, online study group - Part 1 (2019) - fast.ai Course Forums

A Visual Explanation of Gradient Descent Methods (Momentum, AdaGrad, RMSProp, Adam), by Lili Jiang

Proximal gradient method - Wikipedia

Batch, Mini Batch & Stochastic Gradient Descent, by Sushant Patrikar

4.2 - 1b - Gradient Descent - Wikipedia - Workedout, PDF, Mathematical Optimization

Figure 1 from An overview of gradient descent optimization algorithms

Gradient descent - Wikipedia