Ildus Sadrtdinov
- Lecturer, Doctoral Student:Faculty of Computer Science / Big Data and Information Retrieval School
- Ildus Sadrtdinov has been at HSE University since 2019.
Young Faculty Support Programme (Group of Young Academic Professionals)
Category "New Researchers" (2022)
Postgraduate Studies
1st year of study
Approved topic of thesis: Loss Landscapes of Deep Neural Networks When Fine-tunning from a Pre-trained Model
Academic Supervisor: Vetrov, Dmitry
Courses (2023/2024)
- Deep Learning (Master’s programme; Faculty of Computer Science; 2 year, 1 module)Rus
- Deep Learning (Master’s programme; Faculty of Computer Science; 1 year, 4 module)Rus
- Deep Learning 1 (Bachelor’s programme; Faculty of Computer Science; 3 year, 2, 3 module)Eng
- Past Courses
Courses (2022/2023)
- Deep Learning (Master’s programme; Faculty of Computer Science; 1 year, 4 module)Rus
- Deep Learning 1 (Bachelor’s programme; Faculty of Computer Science; 3 year, 1-3 module)Eng
- Research Seminar "Applied problems of data analysis" (Master’s programme; Faculty of Computer Science; 2 year, 1 module)Rus
- Self-supervised Learning (Bachelor’s programme; Faculty of Computer Science; 4 year, 3 module)Rus
Courses (2021/2022)
- How to Win a Data Science Competition: Learn from Top Kagglers (Bachelor’s programme; Faculty of Computer Science; 4 year, 2, 3 module)Eng
- Introduction to Deep Learning (Bachelor’s programme; Faculty of Computer Science; 3 year, 1-3 module)Eng
- Machine Learning 1 (Bachelor’s programme; Faculty of Computer Science; 3 year, 1, 2 module)Rus
Machine Learning 2 (Bachelor’s programme; Faculty of Computer Science; field of study "01.03.02. Прикладная математика и информатика", field of study "01.03.02. Прикладная математика и информатика"; 3 year, 3, 4 module)Rus
Publications3
- Chapter Sadrtdinov I., Pozdeev Dmitrii, Vetrov D., Lobacheva E. To Stay or Not to Stay in the Pre-train Basin: Insights on Ensembling in Transfer Learning, in: Advances in Neural Information Processing Systems 36 (NeurIPS 2023). Curran Associates, Inc., 2023.
- Chapter Alexander Shabalin, Sadrtdinov I., Evgeniy Shabalin. [Re]“Towards Understanding Grokking”, in: ML Reprobucibility Challenge 2022. , 2023. doi doi (in press)
- Chapter Sadrtdinov I., Chirkova N., Lobacheva E. On the Memorization Properties of Contrastive Learning, in: ICML 2021 Workshop, Overparameterization: Pitfalls & Opportunities. , 2021.
‘Every Article on NeurIPS Is Considered a Significant Result’
Staff members of the HSE Faculty of Computer Science will present 12 of their works at the 37th Conference and Workshop on Neural Information Processing Systems (NeurIPS), one of the most significant events in the field of artificial intelligence and machine learning. This year it will be held on December 10–16 in New Orleans (USA).