Kernel Methods

concepts · 6 notes linked

Related: Deep Learning · Support Vector Machines · Pedro Domingos · Gradient Descent · Large Language Models · Francis Bach · Optimization · Convex Optimization

Notes

• A New Link to an Old Model Could Crack the Mystery of Deep Learning | Quanta Magazine — Infinite-width neural networks mathematically equivalent to kernel machines
• Demystifying Support Vector Machines for Beginners: A Reading List — Curated SVM learning resources for beginners across levels
• Gradient Descent Models Are Kernel Machines (Deep Learning) — Deep networks trained by gradient descent are kernel machines
• Gram matrix - Wikipedia — Matrix of pairwise inner products encoding geometric structure of a vector set
• Machine Learning Research Blog — Francis Bach's blog on optimization theory and ML fundamentals
• What is the kernel trick? Why is it important? — Kernel trick enabling non-linear SVM classification without explicit high-dimensional feature maps