Daniil Tiapkin

42 papers A* 12A 5Journal 24

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Beyond Softmax and Entropy: Improving Convergence Guarantees of Policy Gradients by f-SoftArgmax Parameterization with Coupled Regularization. CoRR Safwan Labbi, Daniil Tiapkin, Paul Mangold, Eric Moulines
2026	J	`jnl`	Learning Shortest Paths with Generative Flow Networks. CoRR Nikita Morozov, Ian Maksimov, Daniil Tiapkin, Sergey Samsonov
2025	J	`jnl`	Accelerating Nash Learning from Human Feedback via Mirror Prox. CoRR Daniil Tiapkin, Daniele Calandriello, Denis Belomestny, Eric Moulines, Alexey Naumov, Kashif Rasul, Michal Valko, Pierre Ménard
2025	J	`jnl`	Adaptive Destruction Processes for Diffusion Samplers. CoRR Timofei Gritsaev, Nikita Morozov, Kirill Tamogashev, Daniil Tiapkin, Sergey Samsonov, Alexey Naumov, Dmitry P. Vetrov, Nikolay Malkin
2025	A	`conf`	Federated UCBVI: Communication-Efficient Federated Regret Minimization with Heterogeneous Agents. AISTATS Safwan Labbi, Daniil Tiapkin, Lorenzo Mancini, Paul Mangold, Eric Moulines
2025	A*	`conf`	Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean Field Games. ICML Antonio Ocello, Daniil Tiapkin, Lorenzo Mancini, Mathieu Laurière, Eric Moulines
2025	J	`jnl`	Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean-Field Games. CoRR Antonio Ocello, Daniil Tiapkin, Lorenzo Mancini, Mathieu Laurière, Eric Moulines
2025	A	`conf`	Narrowing the Gap between Adversarial and Stochastic MDPs via Policy Optimization. AISTATS Daniil Tiapkin, Evgenii Chzhen, Gilles Stoltz
2025	J	`jnl`	On Global Convergence Rates for Federated Policy Gradient under Heterogeneous Environment. CoRR Safwan Labbi, Paul Mangold, Daniil Tiapkin, Eric Moulines
2025	A*	`conf`	On Teacher Hacking in Language Model Distillation. ICML Daniil Tiapkin, Daniele Calandriello, Johan Ferret, Sarah Perrin, Nino Vieillard, Alexandre Ramé, Mathieu Blondel
2025	J	`jnl`	On Teacher Hacking in Language Model Distillation. CoRR Daniil Tiapkin, Daniele Calandriello, Johan Ferret, Sarah Perrin, Nino Vieillard, Alexandre Ramé, Mathieu Blondel
2025	A*	`conf`	Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization. ICLR Timofei Gritsaev, Nikita Morozov, Sergey Samsonov, Daniil Tiapkin
2025	A*	`conf`	Revisiting Non-Acyclic GFlowNets in Discrete Environments. ICML Nikita Morozov, Ian Maksimov, Daniil Tiapkin, Sergey Samsonov
2025	J	`jnl`	Revisiting Non-Acyclic GFlowNets in Discrete Environments. CoRR Nikita Morozov, Ian Maksimov, Daniil Tiapkin, Sergey Samsonov
2025	—	`—`	Sample-Efficient Reinforcement Learning: Exploration, Imitation, and Online Learning. (Apprentissage par renforcement efficace en taille d'échantillon: exploration, imitation et apprentissage séquentiel). Daniil Tiapkin
2025	J	`jnl`	gfnx: Fast and Scalable Library for Generative Flow Networks in JAX. CoRR Daniil Tiapkin, Artem Agarkov, Nikita Morozov, Ian Maksimov, Askar Tsyganov, Timofei Gritsaev, Sergey Samsonov
2024	J	`jnl`	A New Bound on the Cumulant Generating Function of Dirichlet Processes. CoRR Pierre Perrault, Denis Belomestny, Pierre Ménard, Éric Moulines, Alexey Naumov, Daniil Tiapkin, Michal Valko
2024	A*	`conf`	Demonstration-Regularized RL. ICLR Daniil Tiapkin, Denis Belomestny, Daniele Calandriello, Eric Moulines, Alexey Naumov, Pierre Perrault, Michal Valko, Pierre Ménard
2024	J	`jnl`	Federated UCBVI: Communication-Efficient Federated Regret Minimization with Heterogeneous Agents. CoRR Safwan Labbi, Daniil Tiapkin, Lorenzo Mancini, Paul Mangold, Eric Moulines
2024	A	`conf`	Generative Flow Networks as Entropy-Regularized RL. AISTATS Daniil Tiapkin, Nikita Morozov, Alexey Naumov, Dmitry P. Vetrov
2024	A*	`conf`	Improved High-Probability Bounds for the Temporal Difference Learning Algorithm via Exponential Stability. COLT Sergey Samsonov, Daniil Tiapkin, Alexey Naumov, Eric Moulines
2024	J	`jnl`	Improving GFlowNets with Monte Carlo Tree Search. CoRR Nikita Morozov, Daniil Tiapkin, Sergey Samsonov, Alexey Naumov, Dmitry P. Vetrov
2024	A*	`conf`	Incentivized Learning in Principal-Agent Bandit Games. ICML Antoine Scheid, Daniil Tiapkin, Etienne Boursier, Aymeric Capitaine, Eric Moulines, Michael I. Jordan, El-Mahdi El-Mhamdi, Alain Oliviero Durmus
2024	J	`jnl`	Incentivized Learning in Principal-Agent Bandit Games. CoRR Antoine Scheid, Daniil Tiapkin, Etienne Boursier, Aymeric Capitaine, El Mahdi El Mhamdi, Eric Moulines, Michael I. Jordan, Alain Durmus
2024	J	`jnl`	Narrowing the Gap between Adversarial and Stochastic MDPs via Policy Optimization. CoRR Daniil Tiapkin, Evgenii Chzhen, Gilles Stoltz
2024	J	`jnl`	Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization. CoRR Timofei Gritsaev, Nikita Morozov, Sergey Samsonov, Daniil Tiapkin
2023	J	`jnl`	Demonstration-Regularized RL. CoRR Daniil Tiapkin, Denis Belomestny, Daniele Calandriello, Eric Moulines, Alexey Naumov, Pierre Perrault, Michal Valko, Pierre Ménard
2023	A*	`conf`	Fast Rates for Maximum Entropy Exploration. ICML Daniil Tiapkin, Denis Belomestny, Daniele Calandriello, Eric Moulines, Rémi Munos, Alexey Naumov, Pierre Perrault, Yunhao Tang, Michal Valko, Pierre Ménard
2023	J	`jnl`	Fast Rates for Maximum Entropy Exploration. CoRR Daniil Tiapkin, Denis Belomestny, Daniele Calandriello, Eric Moulines, Rémi Munos, Alexey Naumov, Pierre Perrault, Yunhao Tang, Michal Valko, Pierre Ménard
2023	J	`jnl`	Finite-Sample Analysis of the Temporal Difference Learning. CoRR Sergey Samsonov, Daniil Tiapkin, Alexey Naumov, Eric Moulines
2023	J	`jnl`	Generative Flow Networks as Entropy-Regularized RL. CoRR Daniil Tiapkin, Nikita Morozov, Alexey Naumov, Dmitry P. Vetrov
2023	A*	`conf`	Model-free Posterior Sampling via Learning Rate Randomization. NeurIPS Daniil Tiapkin, Denis Belomestny, Daniele Calandriello, Eric Moulines, Rémi Munos, Alexey Naumov, Pierre Perrault, Michal Valko, Pierre Ménard
2023	J	`jnl`	Model-free Posterior Sampling via Learning Rate Randomization. CoRR Daniil Tiapkin, Denis Belomestny, Daniele Calandriello, Eric Moulines, Rémi Munos, Alexey Naumov, Pierre Perrault, Michal Valko, Pierre Ménard
2023	A*	`conf`	Orthogonal Directions Constrained Gradient Method: from non-linear equality constraints to Stiefel manifold. COLT Sholom Schechtman, Daniil Tiapkin, Michael Muehlebach, Éric Moulines
2022	A*	`conf`	From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses. ICML Daniil Tiapkin, Denis Belomestny, Eric Moulines, Alexey Naumov, Sergey Samsonov, Yunhao Tang, Michal Valko, Pierre Ménard
2022	J	`jnl`	From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses. CoRR Daniil Tiapkin, Denis Belomestny, Eric Moulines, Alexey Naumov, Sergey Samsonov, Yunhao Tang, Michal Valko, Pierre Ménard
2022	A*	`conf`	Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees. NeurIPS Daniil Tiapkin, Denis Belomestny, Daniele Calandriello, Eric Moulines, Rémi Munos, Alexey Naumov, Mark Rowland, Michal Valko, Pierre Ménard
2022	J	`jnl`	Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees. CoRR Daniil Tiapkin, Denis Belomestny, Daniele Calandriello, Eric Moulines, Rémi Munos, Alexey Naumov, Mark Rowland, Michal Valko, Pierre Ménard
2022	A	`conf`	Primal-Dual Stochastic Mirror Descent for MDPs. AISTATS Daniil Tiapkin, Alexander V. Gasnikov
2022	J	`jnl`	Stochastic saddle-point optimization for the Wasserstein barycenter problem. Optim. Lett. Daniil Tiapkin, Alexander V. Gasnikov, Pavel E. Dvurechensky
2021	A	`conf`	Improved Complexity Bounds in Wasserstein Barycenter Problem. AISTATS Darina Dvinskikh, Daniil Tiapkin
2020	J	`jnl`	Stochastic Saddle-Point Optimization for Wasserstein Barycenters. CoRR Daniil Tiapkin, Alexander V. Gasnikov, Pavel E. Dvurechensky