Linear Lower Bounds and Conditioning of Differentiable Games

By Adam Ibrahim, Waïss Azizian, Gauthier Gidel, Ioannis Mitliagkas. 2019

53 citations recorded by the source corpus.

Subfields: Mathematical Optimization, 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 Mathematical Optimization

1. Constantinos Daskalakis
2. Simon Lacoste-Julien
3. Asuman E. Ozdaglar
4. Waïss Azizian
5. Ioannis Mitliagkas
6. Noah Golowich
7. Sarath Pattathil
8. Damien Scieur

In Game & Decision Theory

1. Simon Lacoste-Julien
2. Asuman E. Ozdaglar
3. Waïss Azizian
4. Ioannis Mitliagkas
5. Constantinos Daskalakis
6. Gauthier Gidel

Citations in the corpus

• Stochastic Hamiltonian Gradient Methods for Smooth Games (2020, neutral): “…version of the problem has been studied in a number of classic (Korpelevich, 1976; Nemirovski, 2004) and recent results (Mescheder et al., 2017; Ibrahim et al., 2019; Gidel et al., 2018; Daskalakis et al., 2018; Gidel et al., 2019; Mokhtari et al., 2020; Azizian et al., 2020a;b) in various…”
• Accelerating Smooth Games by Manipulating Spectral Shapes (2020, background): “Ibrahim et al. (2019); Azizian et al. (2019) extended this framework to multi-player games, but they consider lower and upper-bounds on the eigenvalues of the Jacobian of the game rather than their distribution in the complex plane.”
• Last Iterate is Slower than Averaged Iterate in Smooth Convex-Concave Saddle Point Problems (2020, methodology): “First we remark that consistency is a standard assumption made in the literature on SCLIs and is satisfied by virtually every SCLI used in practice (see, e.g., Arjevani et al. (2015); Azizian et al. (2019); Ibrahim et al. (2019)).”