Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Next revision
Previous revision
teaching:st24:master-seminar [2024/04/13 22:37]
jschwarz created
teaching:st24:master-seminar [2024/06/11 21:00] (current)
jschwarz [Dates]
Line 1: Line 1:
-===== (MasterSeminar: Score-based Generative Models for Machine Learning ​=====+===== Neural ODE and Generative Modelling ​(Master Seminar=====
  
  
Line 20: Line 20:
 Additionally,​ we will explore a broader generalization involving an infinite number of time steps for noise levels, studying the process using stochastic differential equations. This formulation,​ known as score SDEs, leverages SDEs for noise perturbation and sample generation. The seminar will conclude with a comparison to other possible diffusion models and a discussion of further enhancements in sample generation. Additionally,​ we will explore a broader generalization involving an infinite number of time steps for noise levels, studying the process using stochastic differential equations. This formulation,​ known as score SDEs, leverages SDEs for noise perturbation and sample generation. The seminar will conclude with a comparison to other possible diffusion models and a discussion of further enhancements in sample generation.
  
-The seminar is scheduled for the second ​half of the winter term. Participants interested in reviewing concepts of stochastic differential equations have the option to attend a previous seminar titled [[teaching:​st23:​seminar| Stochastic Differential Equations and Generative Modelling (Proseminar/​Seminar)]],​ which takes place in the first half of the winter term.+The seminar is scheduled for the second half of the winter term.
 ==== Organization ==== ==== Organization ====
  
   * **Prerequisites:​** Basic knowledge in probability theory and statistics ​   * **Prerequisites:​** Basic knowledge in probability theory and statistics ​
-  * **Registration:​** Via Müsli. [[https://​muesli.mathi.uni-heidelberg.de/​lecture/​view/​1757|Link]] +  * **Registration:​** Via email to Jonathan 
-  * **First (organizational) meeting:​**  ​Tuesday17 October ​at 14:00 c.t. +  * **First (organizational) meeting:​**  ​**Fridaythe 26th of April** ​at 14:00 c.t. 
-  * **Time and Location:​** ​Tuesdays ​14:00 c.t. in SR 6+  * **Time and Location:​** ​Friday ​14:00 c.t. (SR 6 in INF205)
  
  
-Further information on the seminar will be announced in the first organizational meeting. For any specific question you can contact [[:people | Daniel Gonzalez, Jonas Cassel]].+Further information on the seminar will be announced in the first organizational meeting. For any specific question you can contact [[:people | Jonathan Schwarz]]. 
 + 
 + 
 +==== Dates ==== 
 + 
 +  * ** 14th of June 2024 ** 
 +     ​* ​ **Neural ordinary differential equations** with Hao 
 +     ​* ​ **An introduction to deep generative modeling** with Ying 
 +  * ** 21st of June 2024 ** 
 +    *  **Score-based generative modeling through stochastic differential equations** with Philipp 
 +     * **Generative modeling by estimating gradients of the data distribution** with Sanmati 
 +    * **Flow matching for generative modeling** with Shijie
  
  
Line 45: Line 56:
   *  **Score-based generative modeling through stochastic differential equations**,//​ Song, Yang and Sohl-Dickstein,​ Jascha and Kingma, Diederik P and Kumar, Abhishek and Ermon, Stefano and Poole, Ben//, ICLR (2021)   *  **Score-based generative modeling through stochastic differential equations**,//​ Song, Yang and Sohl-Dickstein,​ Jascha and Kingma, Diederik P and Kumar, Abhishek and Ermon, Stefano and Poole, Ben//, ICLR (2021)
   *  **Gotta go fast when generating data with score-based models**,// olicoeur-Martineau,​ Alexia and Li, Ke and Piché-Taillefer,​ Rémi and Kachman, Tal and Mitliagkas, Ioannis//, arXiv preprint (2021)   *  **Gotta go fast when generating data with score-based models**,// olicoeur-Martineau,​ Alexia and Li, Ke and Piché-Taillefer,​ Rémi and Kachman, Tal and Mitliagkas, Ioannis//, arXiv preprint (2021)
 +  *  **Flow matching for generative modeling**,//​ Lipman, Yaron and Chen, Ricky TQ and Ben-Hamu, Heli and Nickel, Maximilian and Le, Matt//, arXiv preprint arXiv:​2210.02747