Source Themes

Mixed Newton Method for Optimization in Complex Spaces
In this paper, we modify and apply the recently introduced Mixed Newton Method, which is originally designed for minimizing real-valued …
Nikita Yudin, Roland Hildebrand, Sergey Bakhurin, Alexander Degtyarev, Anna Lisachenko, Ilya Kuruzov, Andrei Semenov, Mohammad Alkousa
PDF Cite DOI arXiv
Gradient Clipping Improves AdaGrad when the Noise Is Heavy-Tailed
Methods with adaptive stepsizes, such as AdaGrad and Adam, are essential for training modern Deep Learning models, especially Large …
Savelii Chezhegov, Yaroslav Klyukin, Andrei Semenov, Aleksandr Beznosikov, Alexander Gasnikov, Samuel Horváth, Martin Takáč, Eduard Gorbunov
PDF Cite Code DOI arXiv
Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning
We propose a novel architecture and method of explainable classification with Concept Bottleneck Models (CBMs). While SOTA approaches to Image Classification task work as a black box, there is a growing demand for models that would provide interpreted results.
Andrei Semenov, Vladimir Ivanov, Aleksandr Beznosikov, Alexander Gasnikov
PDF Cite Code DOI arXiv
Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning
Bregman Proximal Method for Efficient Communications under Similarity
We propose a novel distributed method for monotone variational inequalities and convex-concave saddle point problems arising in various machine learning applications such as game theory and adversarial training. By exploiting similarity our algorithm overcomes communication bottleneck which is a major issue in distributed optimization.
Aleksandr Beznosikov, Darina Dvinskikh, Andrei Semenov, Alexander Gasnikov
PDF Cite DOI arXiv