Calendar

Topics are subject to update.

Class schedule

Date

Event

Assignment

Reading

Sep/5

Lecture 1 Foundations of machine learning

HW0 out

[M1]
Ch1

Sep/6

No Problem session

Sep/10

Lecture 2 Parameter estimation

HW0 due
HW1 out

[M1]
Ch4.2

Sep/12

Lecture 3 Bayesian view of estimation

[M1]
Ch 4.6.1–4.6.4

Sep/13

Problem session

Sep/17

Lecture 4 Linear regression

HW1 due
HW2 out

[M1]
Ch 11.1–11.3

Sep/19

Lecture 5 Bayesian linear regression

[M1]
Ch 11.7.1–11.7.5

Sep/20

Student Holiday! No problem session

Sep/24

Lecture 6 Bias/variance, regularization

[M1]
Ch 4.7, 11.3

Sep/26

Lecture 7 Evaluating estimators, consistency

[JWHT] 5.1 (best)

[M1] 5.4.3 (brief)

[SB] 11.2 (optional)

Sep/27

Problem session

Oct/1

Lecture 8 Classification, ranking

HW2 due
HW3 out

[M1]
9.1, 9.2.1–9.2.3, 9.3.1, 9.4, 10.1, 10.2, 10.3.1–3

[B]
4.1–4.3 (another view)

Oct/3

Lecture 9 Online learning, regret

[SB]
Ch 21

Oct/4

Problem session

Oct/8

Lecture 10 Neural networks

HW3 due
MP1 out

[M1]
Ch 18.1-18.4, 13.1

[JWHT]
Ch 8.1, 8.2 (for lecture 10 first part)

Oct/10

Lecture 11 Optimization, regularization

[M1]
Ch 13.2, 13.3, 15.1, 15.2

Oct/11

Problem session

Oct/15

Holiday! No lecture

Oct/17

Lecture 12 Neural network models and problem structures

MP1 due

[B2]
Ch 10, 13

Oct/18

Review sessions

Oct/22

Lecture 13 Over-parameterization, generalization

HW4 out

[B2]
Ch 12

Oct/24

Midterm 7PM–9PM (No lecture)

Oct/25

No problem session

Oct/29

Lecture 14 Robustness, uncertainty quantification

[Here]
Ch 1 & 2

[M2]
Ch 19.8

Oct/31

Lecture 15 Domain adaptation, covariate shift

[M2]
19.1, 19.2, 19.5.2, 19.5.3, 19.5.4

Nov/1

Problem session

Nov/5

Lecture 16 Temporal and spatial data

HW4 due
HW5 out

[M1]
Ch 17 - 17.2

Nov/7

Lecture 17 Handling missing data

[Here]
Ch 1

[M1]
Ch 1.5.5

Nov/8

Problem session

Nov/12

Lecture 18 Dimensionality reduction

[M1]
Ch 20-20.1

Nov/14

Lecture 19 Dimensionality reduction

HW5 due
HW6 out

[M1]
Ch 20-20.4.10

Nov/15

Problem session

Nov/19

Lecture 20 Modeling complex densities

MP2 out

[M1]
Ch 16.3.1–3; 3.5; 8.7; 21.4

Nov/21

Lecture 21 Variational auto-encoders

[M2]
Ch 20; 21.1–2

Nov/22

Problem session

Nov/26

Lecture 22 Diffusion models

HW6 due

[M2]
Ch 25.1–4

Nov/28

Holiday! No lecture

Nov/29

Holiday!! No problem session

Dec/3

Lecture 23 Flow-matching models

[M2]
Ch 23.1

Dec/5

Lecture 24 Some (more) ways to do machine learning wrong!

Dec/6

No problem session

MP2 due

Dec/10

Review