Zobrazeno 1 - 10
of 639
pro vyhledávání: '"Mertikopoulos, P."'
We consider a model of learning and evolution in games whose action sets are endowed with a partition-based similarity structure intended to capture exogenous similarities between strategies. In this model, revising agents have a higher probability o
Externí odkaz:
http://arxiv.org/abs/2407.17815
In this paper, we examine the long-run distribution of stochastic gradient descent (SGD) in general, non-convex problems. Specifically, we seek to understand which regions of the problem's state space are more likely to be visited by SGD, and by how
Externí odkaz:
http://arxiv.org/abs/2406.09241
Motivated by applications to deep learning which often fail standard Lipschitz smoothness requirements, we examine the problem of sampling from distributions that are not log-concave and are only weakly dissipative, with log-gradients allowed to grow
Externí odkaz:
http://arxiv.org/abs/2405.17693
In view of the complexity of the dynamics of learning in games, we seek to decompose a game into simpler components where the dynamics' long-run behavior is well understood. A natural starting point for this is Helmholtz's theorem, which decomposes a
Externí odkaz:
http://arxiv.org/abs/2405.07224
We consider three distinct discrete-time models of learning and evolution in games: a biological model based on intra-species selective pressure, the dynamics induced by pairwise proportional imitation, and the exponential / multiplicative weights (E
Externí odkaz:
http://arxiv.org/abs/2402.09824
Autor:
Sakos, Iosif, Vlatakis-Gkaragkounis, Emmanouil-Vasileios, Mertikopoulos, Panayotis, Piliouras, Georgios
A wide array of modern machine learning applications - from adversarial models to multi-agent reinforcement learning - can be formulated as non-cooperative games whose Nash equilibria represent the system's desired operational states. Despite having
Externí odkaz:
http://arxiv.org/abs/2312.16609
Autor:
Vasconcelos, Francisca, Vlatakis-Gkaragkounis, Emmanouil-Vasileios, Mertikopoulos, Panayotis, Piliouras, Georgios, Jordan, Michael I.
Recent developments in domains such as non-local games, quantum interactive proofs, and quantum generative adversarial networks have renewed interest in quantum game theory and, specifically, quantum zero-sum games. Central to classical game theory i
Externí odkaz:
http://arxiv.org/abs/2311.10859
In this paper, we study the problem of learning in quantum games - and other classes of semidefinite games - with scalar, payoff-based feedback. For concreteness, we focus on the widely used matrix multiplicative weights (MMW) algorithm and, instead
Externí odkaz:
http://arxiv.org/abs/2311.02423
In this paper, we examine the long-run behavior of regularized, no-regret learning in finite games. A well-known result in the field states that the empirical frequencies of no-regret play converge to the game's set of coarse correlated equilibria; h
Externí odkaz:
http://arxiv.org/abs/2311.02407
Many modern machine learning applications - from online principal component analysis to covariance matrix identification and dictionary learning - can be formulated as minimization problems on Riemannian manifolds, and are typically solved with a Rie
Externí odkaz:
http://arxiv.org/abs/2311.02374