6 papers · 1 filter
Uncertainty Quantification of Click and Conversion Estimates for the Autobidding
Ivan Zhigalskii, Andrey Pudovikov, Aleksandr Katrutsa +1
Modern e-commerce platforms employ various auction mechanisms to allocate paid slots for a given item. To scale this approach to the millions of auctions, the platforms suggest pro…
Empirical evaluation of the Frank-Wolfe methods for constructing white-box adversarial attacks
Kristina Korotkova, Aleksandr Katrutsa
The construction of adversarial attacks for neural networks appears to be a crucial challenge for their deployment in various services. To estimate the adversarial robustness of a…
Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models
Tatyana Matveeva, Aleksandr Katrutsa, Evgeny Frolov
Adaptive gradient methods like Adagrad and its variants are widespread in large-scale optimization. However, their use of diagonal preconditioning matrices limits the ability to ca…
NNTile: a machine learning framework capable of training extremely large GPT language models on a single node
Aleksandr Mikhalev, Aleksandr Katrutsa, Konstantin Sozykin +1
This study presents an NNTile framework for training large deep neural networks in heterogeneous clusters. The NNTile is based on a StarPU library, which implements task-based para…
Functional multi-armed bandit and the best function identification problems
Yuriy Dorn, Aleksandr Katrutsa, Ilgam Latypov +1
Bandit optimization usually refers to the class of online optimization problems with limited feedback, namely, a decision maker uses only the objective value at the current point t…
Fast UCB-type algorithms for stochastic bandits with heavy and super heavy symmetric noise
Yuriy Dorn, Aleksandr Katrutsa, Ilgam Latypov +1
In this study, we propose a new method for constructing UCB-type algorithms for stochastic multi-armed bandits based on general convex optimization methods with an inexact oracle.…