5 papers
Curvature-Aligned Probing for Local Loss-Landscape Stabilization
Nikita Kiselev, Andrey Grabovoy
Local loss-landscape stabilization under sample growth is typically measured either pointwise or through isotropic averaging in the full parameter space. Despite practical value, b…
Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation
Vladimir Arkhipkin, Vladimir Korviakov, Nikolai Gerasimenko +22
This report introduces Kandinsky 5.0, a family of state-of-the-art foundation models for high-resolution image and 10-second video synthesis. The framework comprises three core lin…
Closing the Curvature Gap: Full Transformer Hessians
Egor Petrov, Nikita Kiselev, Vladislav Meshkov +1
The optimization landscape of Transformer models remains poorly understood despite their widespread adoption. While recent studies have derived curvature properties for isolated se…
Unraveling the Hessian: A Key to Smooth Convergence in Loss Function Landscapes
Nikita Kiselev, Andrey Grabovoy
The loss landscape of neural networks is a critical aspect of their training, and understanding its properties is essential for improving their performance. In this paper, we inves…
Decentralized Optimization with Coupled Constraints
Demyan Yarmoshik, Alexander Rogozin, Nikita Kiselev +3
We consider the decentralized minimization of a separable objective , where the variables are coupled through an affine constraint $\sum_{i=1}^n\left(\math…