Igor Krawczuk (2024)

Research Interests:

  • Neuromorphic Engineering
  • Machine Learning
  • Data Science
  • Information Theory

Biographie

I have finished my doctoral studies in February 2024 working on using memristive devices as components in neuromorphic machine learning. My research focuses on neuromorphic engineering, trying to bridge the physical models of memristive with machine and the theory of machine learning/information theory and the application of AI to speed up research and technological development.
Further professional interests are data science,automation high performance software engineering and decentralized/distributed computing.

 

Publications

Graph generative deep learning models with an application to circuit topologies

I. Krawczuk / V. Cevher; Y. Leblebici (Dir.)  

Lausanne, EPFL, 2024. 

Distributed Extra-Gradient With Optimal Complexity And Communication Guarantees

A. Ramezani-Kebrya; K. Antonakopoulos; I. Krawczuk; J. Deschenaux; V. Cevher 

2023. 11th International Conference on Learning Representations (ICLR), Kigali, Rwanda, May 1-5, 2023.

Finding Actual Descent Directions For Adversarial Training

F. Latorre; I. Krawczuk; L. T. Dadi; T. M. Pethick; V. Cevher 

2023. 11th International Conference on Learning Representations (ICLR), Kigali, Rwanda, May 1-5, 2023.

DiGress: Discrete Denoising diffusion for graph generation

C. Vignac; I. Krawczuk; A. Siraudin; B. Wang; V. Cevher et al. 

2023. 11th International Conference on Learning Representations (ICLR), Kigali, Rwanda, May 1-5, 2023.

Proximal Point Imitation Learning

L. Viano; A. Kamoutsi; G. Neu; I. Krawczuk; V. Cevher 

2022. 36th Conference on Neural Information Processing Systems (NeurIPS), New Orleans, USA, November 28 – December 3, 2022.

A Computational Turn in Policy Process Studies: Coevolving Network Dynamics of Policy Change

M. Stauffer; I. Mengesha; K. Seifert; I. Krawczuk; J. Fischer et al. 

Complexity. 2022-04-13. Vol. 2022, p. 8210732. DOI : 10.1155/2022/8210732.

Filling gaps in trustworthy development of AI

S. Avin; H. Belfield; M. Brundage; G. Krueger; J. Wang et al. 

Science. 2021-12-10. Vol. 374, num. 6573, p. 1327-1329. DOI : 10.1126/science.abi7176.

Multi-ReRAM synapses for artificial neural network training

I. Boybat; C. Giovinazzo; E. Shahrabi; I. Krawczuk; J. Giannopoulos et al. 

2019-01-01. IEEE International Symposium on Circuits and Systems (IEEE ISCAS), Sapporo, JAPAN, May 26-29, 2019. DOI : 10.1109/ISCAS.2019.8702714.

Effect of metal buffer layer and thermal annealing on HfOx-based ReRAMs

J. Sandrini; B. Attarimashalkoubeh; E. Shahrabi; I. Krawczuk; Y. Leblebici 

2016. International Conference on the Science of Electrical Engineering (ICSEE), Eilat, Israel, September 16-18 November, 2016. DOI : 10.1109/ICSEE.2016.7806101.