Yury Maximov Papers

AAAI Conference 2026 Short Paper

Efficient Contextual Bandit Learning via Reward-Space Sampling and Online Optimization (Student Abstract)

Egor Suraveikin
Dastan Omirzak
Roman Sultimov
Yury Maximov

The contextual multi-armed bandit problem underlies applications in recommendations, e-commerce, finance, and healthcare, where balancing exploration and exploitation is critical. While algorithms such as Upper Confidence Bound (UCB) and Thompson Sampling (TS) achieve strong theoretical guarantees, they often incur heavy computational cost from high-dimensional parameter estimation. We propose a new approach that combines reward sampling with online stochastic optimization. At each round, the algorithm samples hypothetical rewards for all actions and selects the action with the largest draw; the observed reward then updates the model via stochastic optimization. This design is both simple and efficient, preserving exploration while avoiding the pitfalls of greedy behavior on near-duplicate arms. Across synthetic and real-world datasets, our method attains near-optimal reward more quickly and with substantially lower computation than TS and UCB, demonstrating that sampling directly in reward space can improve both statistical efficiency and scalability.

PDF Details DOI

AAMAS Conference 2026 Conference Paper

LLM-Guided Multi-Agent Evacuation Coordination via Episodic Memory and Cognitive Task Analysis

Roman Sultimov
Aleksandr Volkov
Mile Mitrovic
Yury Maximov

We demonstrate 1 an LLM-guided multi-agent platform for coordinating evacuations during wildfires. A lightweight Commander agent observes traffic congestion and wildfire spread in a simulated environment and issues high-level routing decisions that mimic emergency management actions. User agents receive these decisions, locally observe nearby behavior, and choose how to evacuate. We design the Commander to be safe, interpretable, and intended to transfer across settings (number of agents, geographies, wildfire scenarios). On a synthetic city benchmark with 150 user agents, our reinforcement learning policy achieves strong in-distribution performance(92. 6%evacuationrate)butdegradesunderazero-shotfire shift to 67. 1%. The LLM Commander improves the zero-shot evacuation rate to 74. 2% without memory, and up to 82. 5% with episodic memory, mainly by reducing agent timeouts. We also introduce a cognitive task analysis perspective that makes the Commander decision making process fully auditable by humans. Our interactive demo illustrates these results and supports debugging, ablations, and future learning for both AI systems and human operators.

PDF

AAAI Conference 2026 System Paper

RESPOND: Realistic Environment Simulation of Population and Natural Disasters with LLM-Driven Agents

Roman Sultimov
Mikhail Mozikov
Dmitrii Abramov
Mariia Kovalchuk
Maksim Malykh
Ilya Makarov
Andrei Osiptsov
Aleksandr Volkov

Climate change is driving more frequent and severe disasters, putting people and infrastructure at risk. Protecting communities requires models that capture both natural disasters dynamics and how people behave under extreme conditions. This demo presents RESPOND, a multi-agent LLM-enhanced platform that jointly simulates natural hazards and human response. RESPOND couples high-fidelity flood AI forecasting an agent-based model of human behavior. LLM modules improve each agent decision-making, enabling context-aware reasoning over alerts, road closures, social signals, and changing water levels. The system simulates evacuation flows, resource seeking, and communication patterns producing actionable outputs for emergency management, urban planning, and policy. In the live demo one can run what-if or predicted scenarios, adjust assumptions, and observe emergent population behavior and risk hot spots in real time. By tightly coupling dynamic hazards with LLM-driven multi-agent behavior, RESPOND moves beyond fragmented tools and offers a practical, integrated platform for disaster preparedness and response.

PDF Details DOI

AAAI Conference 2026 Short Paper

RESPOND: Realistic Environment Simulation of Population and Natural Disasters with LLM-Driven Agents (Student Abstract)

Roman Sultimov
Mikhail Mozikov
Dmitrii Abramov
Mariia Kovalchuk
Maksim Malykh
Aleksandr Volkov
Ilya Makarov
Andrei Osiptsov

Climate change is driving more frequent and severe disasters, putting people and infrastructure at risk. Protecting communities requires models that capture both natural disasters dynamics and how people behave under extreme conditions. This demo presents RESPOND, a multi-agent LLM-enhanced platform that jointly simulates natural hazards and human response. RESPOND couples high-fidelity flood AI forecasting an agent-based model of human behavior. LLM modules improve each agent decision-making, enabling context-aware reasoning over alerts, road closures, social signals, and changing water levels. The system simulates evacuation flows, resource seeking, and communication patterns producing actionable outputs for emergency management, urban planning, and policy. In the live demo one can run what-if or predicted scenarios, adjust assumptions, and observe emergent population behavior and risk hot spots in real time. By tightly coupling dynamic hazards with LLM-driven multi-agent behavior, RESPOND moves beyond fragmented tools and offers a practical, integrated platform for disaster preparedness and response.

PDF Details DOI

JAIR Journal 2021 Journal Article

Learning over No-Preferred and Preferred Sequence of Items for Robust Recommendation

Aleksandra Burashnikova
Yury Maximov
Marianne Clausel
Charlotte Laclau
Franck Iutzeler
Massih-Reza Amini

In this paper, we propose a theoretically supported sequential strategy for training a large-scale Recommender System (RS) over implicit feedback, mainly in the form of clicks. The proposed approach consists in minimizing pairwise ranking loss over blocks of consecutive items constituted by a sequence of non-clicked items followed by a clicked one for each user. We present two variants of this strategy where model parameters are updated using either the momentum method or a gradient-based approach. To prevent updating the parameters for an abnormally high number of clicks over some targeted items (mainly due to bots), we introduce an upper and a lower threshold on the number of updates for each user. These thresholds are estimated over the distribution of the number of blocks in the training set. They affect the decision of RS by shifting the distribution of items that are shown to the users. Furthermore, we provide a convergence analysis of both algorithms and demonstrate their practical efficiency over six large-scale collections with respect to various ranking measures and computational time.

PDF Details DOI

IJCAI Conference 2019 Conference Paper

Entropy-Penalized Semidefinite Programming

Mikhail Krechetov
Jakub Marecek
Yury Maximov
Martin Takac

Low-rank methods for semi-definite programming (SDP) have gained a lot of interest recently, especially in machine learning applications. Their analysis often involves determinant-based or Schatten-norm penalties, which are difficult to implement in practice due to high computational efforts. In this paper, we propose Entropy-Penalized Semi-Definite Programming (EP-SDP), which provides a unified framework for a broad class of penalty functions used in practice to promote a low-rank solution. We show that EP-SDP problems admit an efficient numerical algorithm, having (almost) linear time complexity of the gradient computation; this makes it useful for many machine learning and optimization problems. We illustrate the practical efficiency of our approach on several combinatorial optimization and machine learning problems.

PDF Details

ICML Conference 2019 Conference Paper

Inference and Sampling of $K_33$-free Ising Models

Valerii Likhosherstov
Yury Maximov
Michael Chertkov

We call an Ising model tractable when it is possible to compute its partition function value (statistical inference) in polynomial time. The tractability also implies an ability to sample configurations of this model in polynomial time. The notion of tractability extends the basic case of planar zero-field Ising models. Our starting point is to describe algorithms for the basic case, computing partition function and sampling efficiently. Then, we extend our tractable inference and sampling algorithms to models whose triconnected components are either planar or graphs of $O(1)$ size. In particular, it results in a polynomial-time inference and sampling algorithms for $K_{33}$ (minor)-free topologies of zero-field Ising models—a generalization of planar graphs with a potentially unbounded genus.

Details

JAIR Journal 2018 Journal Article

Rademacher Complexity Bounds for a Penalized Multi-class Semi-supervised Algorithm

Yury Maximov
Massih-Reza Amini
Zaid Harchaoui

We propose Rademacher complexity bounds for multi-class classifiers trained with a two-step semi-supervised model. In the first step, the algorithm partitions the partially labeled data and then identifies dense clusters containing k predominant classes using the labeled training examples such that the proportion of their non-predominant classes is below a fixed threshold stands for clustering consistency. In the second step, a classifier is trained by minimizing a margin empirical loss over the labeled training set and a penalization term measuring the disability of the learner to predict the k predominant classes of the identified clusters. The resulting data-dependent generalization error bound involves the margin distribution of the classifier, the stability of the clustering technique used in the first step and Rademacher complexity terms corresponding to partially labeled training data. Our theoretical result exhibit convergence rates extending those proposed in the literature for the binary case, and experimental results on different multi-class classification problems show empirical evidence that supports the theory.

PDF Details DOI

IJCAI Conference 2018 Conference Paper

Rademacher Complexity Bounds for a Penalized Multi-class Semi-supervised Algorithm (Extended Abstract)

Yury Maximov
Massih-Reza Amini
Zaid Harchaoui

We propose Rademacher complexity bounds for multi-class classifiers trained with a two-step semi-supervised model. In the first step, the algorithm partitions the partially labeled data and then identifies dense clusters containing k predominant classes using the labeled training examples such that the proportion of their non-predominant classes is below a fixed threshold stands for clustering consistency. In the second step, a classifier is trained by minimizing a margin empirical loss over the labeled training set and a penalization term measuring the disability of the learner to predict the k predominant classes of the identified clusters. The resulting data-dependent generalization error bound involves the margin distribution of the classifier, the stability of the clustering technique used in the first step and Rademacher complexity terms corresponding to partially labeled training data. Our theoretical result exhibit convergence rates extending those proposed in the literature for the binary case, and experimental results on different multi-class classification problems show empirical evidence that supports the theory.

PDF Details

NeurIPS Conference 2017 Conference Paper

Aggressive Sampling for Multi-class to Binary Reduction with Applications to Text Classification

Bikash Joshi
Massih R. Amini
Ioannis Partalas
Franck Iutzeler
Yury Maximov

We address the problem of multi-class classification in the case where the number of classes is very large. We propose a double sampling strategy on top of a multi-class to binary reduction strategy, which transforms the original multi-class problem into a binary classification problem over pairs of examples. The aim of the sampling strategy is to overcome the curse of long-tailed class distributions exhibited in majority of large-scale multi-class classification problems and to reduce the number of pairs of examples in the expanded data. We show that this strategy does not alter the consistency of the empirical risk minimization principle defined over the double sample reduction. Experiments are carried out on DMOZ and Wikipedia collections with 10, 000 to 100, 000 classes where we show the efficiency of the proposed approach in terms of training and prediction time, memory consumption, and predictive performance with respect to state-of-the-art approaches.

PDF Details

Possible papers