Skip to content
lectern.tv
1/4
Mathematical Foundations of Machine Learning →0/7
1

The Geometry of Linear Equations

Gilbert Strang · 39:49

2

Transposes, Permutations & Vector Spaces R^n

Gilbert Strang · 47:41

3

Convex Functions — First/Second-Order Conditions & Epigraphs

Stephen Boyd · 1:17:14

4

Saddle-Point Interpretation, KKT Conditions & Perturbation

Stephen Boyd · 1:09:19

5

The Learning Problem

Yaser Abu-Mostafa · 1:21:27

6

Is Learning Feasible?

Yaser Abu-Mostafa · 1:16:48

7

Building makemore Part 3: Activations, Gradients, Kaiming Init & BatchNorm

Andrej Karpathy · 1:55:57

Saddle-Point Interpretation, KKT Conditions & Perturbation

Stephen BoydDistinguishedStanford University

Samsung Professor in the School of Engineering

1:09:19·2008·graduate level
Path step 4: Introduces saddle-point geometry, KKT optimality, and Lagrangian duality.

Derives Karush-Kuhn-Tucker optimality conditions, complementary slackness, and shadow-price sensitivity analysis ∂p*/∂uᵢ = -λᵢ*.

EngineeringConvex OptimizationSignal Processing & RoboticsKKT ConditionsShadow Prices

Professor Stephen Boyd, of the Stanford University Electrical Engineering department, continues his lecture on convex optimization problems for the course, Convex Optimization I (EE 364A).

Source: Stanford via YouTubeWatch on YouTube
LecturerAll lecturers →
Stephen BoydDistinguished

Samsung Professor of Engineering, Stanford & Co-Author of Convex Optimization

Samsung Professor of Engineering at Stanford whose textbook and EE364a lectures established convex optimization as a core language across control, signal processing, and ML.

2 courses · 43 lecturesCanon
Previous · Step 3

Convex Functions — First/Second-Order Conditions & Epigraphs

Next · Step 5

The Learning Problem

Comments

Add a comment...Sign in