Zobrazeno 1 - 10
of 125
pro vyhledávání: '"Naumov, Alexey"'
Generative Flow Networks (GFlowNets) treat sampling from distributions over compositional discrete spaces as a sequential decision-making problem, training a stochastic policy to construct objects step by step. Recent studies have revealed strong con
Externí odkaz:
http://arxiv.org/abs/2406.13655
Autor:
Gorbunov, Mikhail, Yudin, Nikolay, Soboleva, Vera, Alanov, Aibek, Naumov, Alexey, Rakhuba, Maxim
The increasing size of neural networks has led to a growing demand for methods of efficient fine-tuning. Recently, an orthogonal fine-tuning paradigm was introduced that uses orthogonal matrices for adapting the weights of a pretrained model. In this
Externí odkaz:
http://arxiv.org/abs/2406.10019
In this paper, we obtain the Berry-Esseen bound for multivariate normal approximation for the Polyak-Ruppert averaged iterates of the linear stochastic approximation (LSA) algorithm with decreasing step size. Our findings reveal that the fastest rate
Externí odkaz:
http://arxiv.org/abs/2405.16644
Autor:
Mangold, Paul, Samsonov, Sergey, Labbi, Safwan, Levin, Ilya, Alami, Reda, Naumov, Alexey, Moulines, Eric
In this paper, we analyze the sample and communication complexity of the federated linear stochastic approximation (FedLSA) algorithm. We explicitly quantify the effects of local training with agent heterogeneity. We show that the communication compl
Externí odkaz:
http://arxiv.org/abs/2402.04114
Autor:
Tiapkin, Daniil, Belomestny, Denis, Calandriello, Daniele, Moulines, Eric, Munos, Remi, Naumov, Alexey, Perrault, Pierre, Valko, Michal, Menard, Pierre
In this paper, we introduce Randomized Q-learning (RandQL), a novel randomized model-free algorithm for regret minimization in episodic Markov Decision Processes (MDPs). To the best of our knowledge, RandQL is the first tractable model-free posterior
Externí odkaz:
http://arxiv.org/abs/2310.18186
Autor:
Tiapkin, Daniil, Belomestny, Denis, Calandriello, Daniele, Moulines, Eric, Naumov, Alexey, Perrault, Pierre, Valko, Michal, Menard, Pierre
Incorporating expert demonstrations has empirically helped to improve the sample efficiency of reinforcement learning (RL). This paper quantifies theoretically to what extent this extra information reduces RL's sample complexity. In particular, we st
Externí odkaz:
http://arxiv.org/abs/2310.17303
In this paper we consider the problem of obtaining sharp bounds for the performance of temporal difference (TD) methods with linear function approximation for policy evaluation in discounted Markov decision processes. We show that a simple algorithm
Externí odkaz:
http://arxiv.org/abs/2310.14286
The recently proposed generative flow networks (GFlowNets) are a method of training a policy to sample compositional discrete objects with probabilities proportional to a given reward via a sequence of actions. GFlowNets exploit the sequential nature
Externí odkaz:
http://arxiv.org/abs/2310.12934
Autor:
Beznosikov, Aleksandr, Samsonov, Sergey, Sheshukova, Marina, Gasnikov, Alexander, Naumov, Alexey, Moulines, Eric
This paper delves into stochastic optimization problems that involve Markovian noise. We present a unified approach for the theoretical analysis of first-order gradient methods for stochastic optimization and variational inequalities. Our approach co
Externí odkaz:
http://arxiv.org/abs/2305.15938
In this work, we derive sharp non-asymptotic deviation bounds for weighted sums of Dirichlet random variables. These bounds are based on a novel integral representation of the density of a weighted Dirichlet sum. This representation allows us to obta
Externí odkaz:
http://arxiv.org/abs/2304.03056