Posts

“Enhancing LLM Training via Spectral Clipping” – joint work with Xiaowen Jiang and Sebastian U. Stich.

“Gradient-Normalized Smoothness for Optimization with Approximate Hessians” – joint work with Martin Jaggi and Nikita Doikov.

“Adaptive Regularized Newton Method with Inexact Hessian” – joint work with Aleksandr Shestakov, Nail Bashirov, Alexander Gasnikov, Martin Takáč, Aleksandr Beznosikov and Dmitry Kamzolov.

Between December 2 and December 7, I will attend EurIPS 2025 in Copenhagen, an event officially endorsed by NeurIPS. I will present two papers there: “Benchmarking Optimizers for Large Language Model Pretraining” and “Just a Simple Transformation is Enough for Data Protection in Split Learning”.

“Adaptive Regularized Newton Method with Inexact Hessian” – joint work with Aleksandr Shestakov, Nail Bashirov, Alexander Gasnikov, Martin Takáč, Aleksandr Beznosikov and Dmitry Kamzolov.

“Apertus: Democratizing Open and Compliant LLMs for Global Language Environments” – a project by Team Apertus within the Swiss AI Initiative.

“Benchmarking Optimizers for Large Language Model Pretraining” – joint work with Matteo Pagliardini and Martin Jaggi.

“Gradient-Normalized Smoothness for Optimization with Approximate Hessians” – joint work with Martin Jaggi and Nikita Doikov.

“Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed” (with Savelii Chezhegov, Yaroslav Klyukin, Aleksandr Beznosikov, Alexander Gasnikov, Samuel Horváth, Martin Takáč and Eduard Gorbunov).

Between 15 February and 15 April, I will work as a Visiting Student at the Machine Learning Department of MBZUAI under the supervision of Professor Martin Takáč.