Weekly outline

  • This master class on learning theory covers the classical PAC framework for learning, stochastic gradient descent, tensor methods. We also touch upon topics from the recent literature on mean field methods for NN and the double descent phenomenon.

    Teacher: Nicolas Macris: nicolas.macris@epfl.ch  

    Teaching Assitant: Perrine Vantalon - perrine.vantalon@epfl.ch

    Courses: Mondays 8h15-10h Room INM202; Exercises: Tuesdays 17h15-19h Room INR219.

    We will use this moodle page to distribute homeworks, solutions, and lecture material each week. As well as use the discussion and questions forum. Dont hesitate to actively use this forum.

    MIDTERM: there will be a midterm on monday March 30 at 8h15 - 10h in room INM202. This will count 30% towards the final grade. Its open book (you can bring your notes, printed material, the UML book, or download material on your laptop before hand and have wifi switched off). 

    EXAM: the final exam during official exam session will count for 70% of the final grade. Its open book (you can bring your notes, printed material, the UML book, or download material on your laptop before hand and have wifi switched off). 

    Textbooks and notes:


  • 16 - 17 February: no class

    Week of 23rd-24th we will have class on monday (during regular time) and also on tuesday (during exercise session time)

  • 23 - 24 February

    1. Monday 23: PAC learning framework. Finite classes. Uniform convergence.

    See chapters 3 and 4 in UML

    Homework 1: exercises 1, 3, 7, 8 of Chapter 3 (discussed in exercise session next week)

    2. Tuesday 24: No free lunch theorem.

    See chapter 5 in UML

    Homework 2: exercises 1 and 2 of chapter 4 + extra on proof of Hoeffding's inequality (discussed in exercise session next week)

  • 2 - 3 March

    Learning infinite classes

    Chapter 6 in UML

    Homework 1: exercises 1, 3, 7, 8 of Chapter 3

    Homework 2: exercises 1 and 2 of chapter 4 + extra on proof of Hoeffding's inequality

  • 9 - 10 March

    Bias variance tradeoff and the double descent phenomenon 

    We will study the double descent of generalization error based on the paper "Two models of double descent for weak features" by Belkin, Hsu, Xu

  • 16 - 17 March

    Double descent continued
  • 23 - 24March

    Gradient descent (convexity, Lipshitzness, Approach to optimal solution)

    Stochastic gradient descent, application to learning

    Chapter 14 in UML

  • 30 March: midterm

    MIDTERM monday 30 march 8h15 - 10h room INM 202

  • 6 - 7 April Easter break

  • 13 - 14 April

    Mean field approach for two layer neural networks

    based on the paper "One lecture on two layer neural networks" by A. Montanari

  • 20 - 21 April

    We finish discussing the main idea of the mean field analysis of two layer neural networks (notably part II of notes).

    Homework: we have extra homework 7 on convexity, GD, SGD below.

  • 27 - 28 April

    Tensors 1. Motivations and examples, multi-dimensional arrays, tensor product, tensor rank.

    Tensors 2. Tensor rank and decompositions, Jennrich's theorem (proof of thm next time)

  • 4 - 5 May

    Tensors 2bis. Jennrich's algorithm (proofs)

  • 11 -12 May

    Tensors 3. Alternating least square algorithm

  • 18 - 19 May

     Tensors 4. Multilinear rank Tucker higher order singular value decomposition

  • Tuesday 26 May (monday is a holiday)

    Tensors 5. Power method and Applications: Gaussian Mixture Models, Topic models of documents

  • Old exams

    Here we will post old exams with solutions which will allow you to train yourself. Note that some problems (but not all) are included in the current year's material.

  • Further lecture notes