Blog

What we've shipped

Browse our research.

Filter

23 of 23 posts
Search index →
Paper Proceedings of the ACM Web Conference 2026 · 2026

VK-LSVD: A Large-Scale Industrial Dataset for Short-Video Recommendation

We introduce the VK Large Short-Video Dataset (VK-LSVD), the largest publicly available industrial dataset of its kind.

Alexander Poplavsky, Alexander D'yakonov, Yuriy Dorn, Andrey Zimovnov

arXiv Read →
Paper arXiv · 2026

Practical MCTS-based Query Optimization: A Reproducibility Study and new MCTS algorithm for complex queries

Vladimir Burlakov, Alena Rybakina, Sergey Kudashev, Konstantin Gilev, Alexander Demin, Denis Ponomaryov, Yuriy Dorn

arXiv Read →
Paper arXiv · 2026

Uncertainty Quantification of Click and Conversion Estimates for the Autobidding

We propose the DenoiseBid method, which corrects the generated CTRs and CVRs to make the resulting bids more efficient in auctions.

Ivan Zhigalskii, Andrey Pudovikov, Aleksandr Katrutsa, Egor Samosvat

arXiv Read →
Journal Doklady Mathematics · 2026

Survey of Modern Smooth Optimization Algorithms with Comparison Oracle

This review provides an overview of contemporary algorithms for smooth, multivariate optimization that utilize only information about the order of the function values, rather than their numerical magnitudes.

Aleksandr Lobanov, Alexander Gasnikov

Paper Link Read →
Journal Optimization Methods and Software · 2026

Zeroth-order methods for non-smooth stochastic problems under heavy-tailed noise

We propose gradient-free algorithms with zeroth-order oracle under adversarial noise with unbounded variance, for non-smooth convex and convex-concave optimization problems.

Nail Bashirov, Alexander Gasnikov, Aleksandr Lobanov

Taylor & Francis Read →
Journal Journal of Mathematical Sciences · 2026

IDENTIFICATION OF THE BRAESS PARADOX IN A STABLE DYNAMIC MODEL IN NETWORK WITH ONE SOURCE AND MULTIPLE SINKS

We study the problem of identifying edges in a transportation graph where the introduction of an additional toll would enhance the efficiency of network usage within the Nesterov–de Palma equilibrium model.

Oleg Shitikov, Yuriy Dorn

Springer Read →
Paper APEIE 2025 · 2025

Hint Based Query Optimization with LLM Agent and Plan Similarity

A two–path architecture for query–optimizer hint selection that combines fast nearest–neighbor transfer in an LLM–derived plan–embedding space with a budgeted LLM agent that searches the hint space under DBMS feedback.

Nikita Vasilenko, Alexander Demin, Vladimir Burlakov

ResearchGate Read →
Paper arXiv · 2025

UCB-type Algorithm for Budget-Constrained Expert Learning

We introduce M-LCB, a computationally efficient UCB-style meta-algorithm that provides anytime regret guarantees.

Ilgam Latypov, Alexandra Suvorikova, Alexey Kroshnin, Alexander Gasnikov, Yuriy Dorn

arXiv Read →
Paper arXiv · 2025

Autobidding Arena: unified evaluation of the classical and RL-based autobidding algorithms

Andrey Pudovikov, Aleksandra Khirianova, Ekaterina Solodneva, Aleksandr Katrutsa, Egor Samosvat, Yuriy Dorn

arXiv Read →
Paper AAMAS 2026 · 2025

RARe: Raising Ad Revenue Framework with Context-Aware Reranking

We propose and compare two different click models that take into account the context of items in a search result.

Ekaterina Solodneva, Aleksandra Khirianova, Aleksandr Katrutsa, Roman Loginov, Andrey Tikhanov, Egor Samosvat, Yuriy Dorn

arXiv Read →
Paper AAMAS 2026 · 2025

Robust autobidding for noisy conversion prediction models

We propose RobustBid, an efficient method for robust autobidding taking into account uncertainty in CTR and CVR predictions.

Andrey Pudovikov, Aleksandra Khirianova, Ekaterina Solodneva, Gleb Molodtsov, Aleksandr Katrutsa, Yuriy Dorn, Egor Samosvat

arXiv Read →
NKph(p)p₀h(p₀)plan space · h: N → K
Paper arXiv · 2025

Training-Free Query Optimization via LLM-Based Plan Similarity

Nikita Vasilenko, Alexander Demin, Vladimir Burlakov

arXiv Read →
Paper AAMAS 2025 · 2025

Fast UCB-type algorithms for stochastic bandits with heavy and super heavy symmetric noise

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.

Yuriy Dorn, Aleksandr Katrutsa, Ilgam Latypov, Andrey Pudovikov

arXiv Read →
Paper Proceedings of the ACM on Web Conference 2025 · 2025

Bat: Benchmark for auto-bidding task

We propose RobustBid, an efficient method for robust autobidding taking into account uncertainty in CTR and CVR predictions.

Aleksandra Khirianova, Ekaterina Solodneva, Andrey Pudovikov, Sergey Osokin, Egor Samosvat, Yuriy Dorn, Alexander Ledovsky, Yana Zenkova

arXiv Read →
Paper AAMAS 2026 · 2025

Functional multi-armed bandit and the best function identification problems

We propose two new classes of problems: the functional multi-armed bandit problem (FMAB) and the best function identification problem.

Yuriy Dorn, Aleksandr Katrutsa, Ilgam Latypov, Anastasiia Soboleva

arXiv Read →
Paper arXiv · 2025

Optimizing Online Advertising with Multi-Armed Bandits: Mitigating the Cold Start Problem under Auction Dynamics

Anastasiia Soboleva, Andrey Pudovikov, Roman Snetkov, Alina Babenko, Egor Samosvat, Yuriy Dorn

arXiv Read →
Paper arXiv · 2025

Optimal Traffic Allocation for Multi-Slot Sponsored Search: Balance of Efficiency and Fairness

We propose a novel ad allocation model that departs from traditional auction mechanics.

Anastasiia Soboleva, Alexander Ledovsky, Yuriy Dorn, Egor Samosvat, Andrey Tikhanov, Fyodor Prazdnikov

arXiv Read →
Paper arXiv · 2025

Power of Generalized Smoothness in Stochastic Convex Optimization: First- and Zero-Order Algorithms

This paper is devoted to the study of stochastic optimization problems under the generalized smoothness assumption.

Aleksandr Lobanov, Alexander Gasnikov

arXiv Read →
Paper Operations Research Forum · 2025

γ-Competitiveness: An Approach to Multi-Objective Optimization with High Computation Costs in Lipschitz Functions

We introduce an extension of the concept of competitive solutions and propose the Scalarization With Competitiveness Method (SWCM) for multi-criteria problems.

Ilgam Latypov, Yuriy Dorn

arXiv Read →
Journal Russian Journal of Nonlinear Dynamics · 2024

On quasi-convex smooth optimization problems by a comparison oracle

This paper is devoted to an approach to minimizing quasi-convex functions using a recently proposed comparison oracle only.

Alexander Gasnikov, Mohammad Alkousa, Aleksandr Lobanov, Yuriy Dorn, Fedor Stonyakin, Ilya Kuruzov, Sanjeev Singh

arXiv Read →
Paper arXiv · 2024

Learning-Augmented Online Caching: New Upper Bounds

Daniel Skachkov, Denis Ponomaryov, Yuriy Dorn, Alexander Demin

arXiv Read →
Paper arXiv · 2024

EEvA: Fast Expert-Based Algorithms for Buffer Page Replacement

Alexander Demin, Yuriy Dorn, Aleksandr Katrutsa, Daniil Kazantsev, Ilgam Latypov, Yulia Maximlyuk, Denis Ponomaryov

arXiv Read →
Journal Computational Management Science · 2024

Implicitly normalized forecaster with clipping for linear and non-linear heavy-tailed multi-armed bandits

Yuriy Dorn, Nikita Kornilov, Nikolay Kutuzov, Alexander Nazin, Eduard Gorbunov, Alexander Gasnikov

arXiv Read →