Artur Pak

According to our database, Artur Pak authored at least 6 papers between 2022 and 2025.

Collaborative distances:

• Dijkstra number of six.
• Erdős number of five.

2025

Gradient descent fails to learn high-frequency functions and modular arithmetic.

Rustem Takhanov, Maxat Tezekbayev, Artur Pak, Arman Bolatov, Zhenisbek Assylbekov

Mach. Learn., April, 2025

Learning Overspecified Gaussian Mixtures Exponentially Fast with the EM Algorithm.

Zhenisbek Assylbekov, Alan Legg, Artur Pak

Proceedings of the Machine Learning and Knowledge Discovery in Databases. Research Track, 2025

2023

Long-Tail Theory Under Gaussian Mixtures.

Arman Bolatov, Maxat Tezekbayev, Igor Melnykov, Artur Pak, Vassilina Nikoulina, Zhenisbek Assylbekov

Proceedings of the ECAI 2023 - 26th European Conference on Artificial Intelligence, September 30 - October 4, 2023, Kraków, Poland, 2023

Intractability of Learning the Discrete Logarithm with Gradient-Based Methods.

Rustem Takhanov, Maxat Tezekbayev, Artur Pak, Arman Bolatov, Zhibek Kadyrsizova, Zhenisbek Assylbekov

Proceedings of the Asian Conference on Machine Learning, 2023

Hardness of Learning AES Key (Student Abstract).

Artur Pak, Sultan Nurmukhamedov, Rustem Takhanov, Zhenisbek Assylbekov

Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022

Hardness of Learning AES Key (Short Paper).

Sultan Nurmukhamedov, Artur Pak, Rustem Takhanov, Zhenisbek Assylbekov

Proceedings of the Discussion Papers - 22nd International Conference of the Italian Association for Artificial Intelligence (AIxIA 2022 DP), Udine, Italy, November 28, 2022