Zur Theorie der Gesellschaftsspiele

By J. Neumann. 1928

Subfields: Probabilistic & Bayesian Methods, Game & Decision Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Probabilistic & Bayesian Methods

In Game & Decision Theory

Citations in the corpus

Generalization and Equilibrium in Generative Adversarial Nets (GANs) (2017, background): “The well-known min-max theorem [v. Neumann, 1928] in game theory shows if both players are allowed to play mixed strategies then the game has a min-max solution.”
Giraffe: Using Deep Reinforcement Learning to Play Chess (2015, methodology): “When von Neumann introduced the minimax algorithm in 1928, he focused on cases where the entire game tree can be explored [4].”
Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goals (2018, methodology): “We enforce monotonicity constraints on 14 of the 16 features, resulting in an additional 9,740 constraints applied during training (each of these is simply a linear inequality constraint on a pair of model parameters); see You et al. (2017), Canini et al.”
How to Train Your DRAGAN (2017, background): “Von Neumann established the minimax theorem for zero-sum games in [1] or equivalently the existence of mixed Nash equilibria.”
Super-efficiency of automatic differentiation for functions defined as a minimum (2020, background): “…instance in reweighted least-squares [Daubechies et al., 2010] where L is smooth but not (cid:96) . two-players In game theory, such problems naturally appear in two-players maximin games[von Neumann, 1928], with applications for instance to generative adversarial nets [Goodfellow et al., 2014].”
Five lectures on optimal transportation: Geometry, regularity and applications (2010, background): “Von Neumann [107] identified structural conditions on the payoff function to have a saddle point (17), in which case equality holds in (15); see also Kakutani’s reference to [108] in [66].”
Evolutionary games on graphs (2006, background): “This is the class where the existence of an equilibrium was first proved in the form of the Minimax Theorem (von Neumann, 1928).”
Solving Partially Observable Stochastic Games with Public Observations (2019, background): “Since any ﬁnite-horizon approximation of a PO-POSGs has a value (von Neumann 1928) and discounted-sum utilities are considered, the value of a PO-POSG is well deﬁned.”
A Domain Agnostic Measure for Monitoring and Evaluating GANs (2018, background): “The ideas of duality and equilibria developed in the seminal work of [33, 22] have become a cornerstone in many ﬁelds of science, but are relatively unexplored for GANs.”
Fast dual minimization of the vectorial total variation norm and applications to color image processing (2008, methodology): “455 c©2008 American Institute of Mathematical Sciences The proposed VTV minimization model is based on the dual formulation of the vectorial TV norm.”
Lower Dimensional Kernels for Video Discriminators (2019, methodology): “Image Generation Adversarial training, within the context of neural networks [10], pits two networks against each other in a zero-sum non-cooperative game which is solved, in the game-theoretic sense, by the application of the minimax theorem [21].”