Notation: “⋆” means equal contribution, “+” means alphabetic orderig.

Preprints:

• D. Tiapkin, D. Calandriello, J. Ferret, S. Perrin, N. Vieillard, A. Ramé, M. Blondel. On Teacher Hacking in Language Model Distillation, 2025.
• N. Morozov, I. Maksimov, D. Tiapkin, S. Samsonov. Revisiting Non-Acyclic GFlowNets in Discrete Environments, 2025.
• P. Perrault, D. Belomestny, P. Ménard, É. Moulines, A. Naumov, D. Tiapkin, M. Valko. A New Bound on the Cumulant Generating Function of Dirichlet Processes, 2024.
• D. Belomestny⁺, P. Ménard⁺, A. Naumov⁺, D. Tiapkin⁺, M. Valko⁺. Sharp Deviations Bounds for Dirichlet Weighted Sums with Application to analysis of Bayesian algorithms, 2023.

Workshop papers:

• N. Morozov, D. Tiapkin, S. Samsonov, A. Naumov, D. Vetrov. Improving GFlowNets with Monte Carlo Tree Search, ICML 2024 SPIGM Workshop.

Conference papers:

• D. Tiapkin, E.Chzhen, G.Stoltz. Narrowing the Gap between Adversarial and Stochastic MDPs via Policy Optimization, AISTATS 2025.
• S. Labbi, D. Tiapkin, L. Mancini, P. Mangold, E. Moulines. Federated UCBVI: Communication-Efficient Federated Regret Minimization with Heterogeneous Agents, AISTATS 2025.
• T. Gritsaev, N. Morozov, S. Samsonov, D. Tiapkin. Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization, ICLR 2025.
• A. Scheid, D. Tiapkin, E. Boursier, A. Capitaine, E. M. El Mhamdi, E. Moulines, M. I. Jordan, A. Durmus. Incentivized Learning in Principal-Agent Bandit Games, ICML 2024.
• S. Samsonov, D. Tiapkin, A. Naumov, É. Moulines. Improved High-Probability Bounds for the Temporal Difference Learning Algorithm via Exponential Stability, COLT 2024.
• D. Tiapkin^⋆, N. Morozov^⋆, A. Naumov, D. Vetrov. Generative Flow Networks as Entropy-Regularized RL, AISTATS 2024 (Oral).
• D. Tiapkin, D. Belomestny, D. Calandriello, É. Moulines, A. Naumov, P. Perrault, M. Valko, P. Ménard. Demonstration-Regularized RL, ICLR 2024.
• D. Tiapkin, D. Belomestny, D. Calandriello, É. Moulines, R. Munos, A. Naumov, P. Perrault, M. Valko, P. Ménard. Model-free Posterior Sampling via Learning Rate Randomization, NeurIPS 2023;
• D. Tiapkin, D. Belomestny, D. Calandriello, É. Moulines, R. Munos, A. Naumov, P. Perrault, Y. Tang, M. Valko, P. Ménard. Fast Rates for Maximum Entropy Exploration, ICML 2023;
• S. Schechtman, D. Tiapkin, É. Moulines, and M. Muehlebach. Orthogonal Directions Constrained Gradient Method: from non-linear equality constraints to Stiefel manifold, COLT 2023;
• D. Tiapkin, D. Belomestny, D. Calandriello, É. Moulines, R. Munos, A. Naumov, M. Rowland, M. Valko, P. Ménard. Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees, NeurIPS 2022;
• D. Tiapkin, D. Belomestny, É. Moulines, A. Naumov, S. Samsonov, Y. Tang, M. Valko, P. Ménard. From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses, ICML 2022 (Oral);
• S. Schechtman, D. Tiapkin, É. Moulines, M. I. Jordan, and M. Muehlebach. First-order Constrained Optimization: Non-smooth Dynamical System Viewpoint, IFAC Workshop on Control Applications of Optimization, 2022
• D. Tiapkin, A. Gasnikov. Primal-Dual Stochastic Mirror Descent for MDPs. AISTATS 2022;
• D. Dvinskikh, D. Tiapkin. Improved Complexity Bounds in the Wasserstein Barycenter Problem, AISTATS 2021.

Journal articles:

• D. Tiapkin, D.Shabanov On the Structure of the Set of Panchromatic Colorings of a Random Hypergraph, Doklady Mathematics, 2023.
• D. Tiapkin, A. Gasnikov, P. Dvurechensky. Stochastic saddle-point optimization for the Wasserstein barycenter problem, Optimization Letters, 2022.