EECE695D: Deep Learning Theory (Fall 2025)
#
Team
#
- Instructor. Jaeho Lee 이재호 ✉️
- TA. Byung-ki Kwon 권병기 ✉️
Location & Time
#
- Class. Mondays/Wednesdays, 2PM–3:30PM, EB2, #109
- Office Hr. Mondays, 5PM–6PM, GoAround Coffee @RIST (plus by request)
Schedule (tentative)
#
- W1. Overview and Basics of Statistical Learning Theory
(9/1, 9/3)
- W2. Approx: Universal approximation with shallow nets
(9/8, 9/10)
- W3. Approx: Infinite-width and kernels
(9/15, 9/17-1, 9/17-2)
- W4. Approx: Benefits of depth
(9/22-1, 9/22-2, 9/24 ) - W5. Optim: Convex optimization and generalizations
(9/29, 10/1) - W6. Chuseok Holidays
- W7. Optim: SGD and flow-based analyses
(10/13, 10/15) - W8. Mid-Term
- W9. Optim: Implicit bias
(10/27, 10/29)
- W10. Gen: Concentration of measures, uniform convergence
(11/3, 11/5)
- W11. Gen: Rademacher complexities, covering numbers
(11/10, 11/12) - W12. Gen: Chaining and VC dimensions
(11/17, 11/19) - W13. Recent Results - 1
(11/24, 11/26) - W14. Recent Results - 2
(12/1, 12/3) - W15. Student Presentations - 1
(team 5, team 2, team 3, team 4) - W16. Student Presentations - 2
(team 1, team 6, team 7, team 8)
Textbook
#