Fetching the paper…
Reading the bibliography…
Unlike nonconvex optimization, where gradient descent is guaranteed to converge to a local optimizer, algorithms for nonconvex-nonconcave minimax optimization can have topologically different solution paths: sometimes converging to a solution, sometimes never converging and instead following a limit cycle, and sometimes diverging.
What is local optimality in nonconvex-nonconcave minimax optimization?
Jin, C., Netrapalli, P., and Jordan, M. I. (2020) · 1902
Earlier work this paper cites.
The stable, center-stable, center, center-unstable, unstable manifolds
Kelley, A. (1967) · 1967
Earlier work this paper cites.
On minimax robustness: A general approach and applications
Verdu, S. and Poor, H. (1984) · 1984
Earlier work this paper cites.
Elements of Applied Bifurcation Theory (2nd Ed.)
Kuznetsov, Y. A. (1998) · 1998
Earlier work this paper cites.
An o ( s r ) o(s^{r}) -resolution ode framework for discrete-time optimization algorithms and applications to the linear convergence of minimax problems
Lu, H. (2020) · 2001
Earlier work this paper cites.
Global convergence and variance-reduced optimization for a class of nonconvex-nonconcave minimax problems
Yang, J., Kiyavash, N., and He, N. (2020) · 2002
Earlier work this paper cites.
On the impossibility of global convergence in multi-loss optimization
Letcher, A. (2020) · 2005
Earlier work this paper cites.
The landscape of the proximal point method for nonconvex-nonconcave minimax optimization
Grimmer, B., Lu, H., Worah, P., and Mirrokni, V. (2020) · 2006
Earlier work this paper cites.
The limits of min-max optimization algorithms: convergence to spurious non-critical sets
Hsieh, Y.-P., Mertikopoulos, P., and Cevher, V. (2020) · 2006
Cited alongside, same era.
Robust optimization
Ben-Tal, A., El Ghaoui, L., and Nemirovski, A. (2009) · 2009
Cited alongside, same era.
Theory and applications of robust optimization
Bertsimas, D., Brown, D. B., and Caramanis, C. (2011) · 2011
Cited alongside, same era.
Generative adversarial nets
Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014) · 2014
Cited alongside, same era.
Saddle-point dynamics: conditions for asymptotic stability of saddle points
Cherukuri, A., Gharesifard, B., and Cortes, J. (2016) · 2016
Cited alongside, same era.
A differential equation for modeling nesterov’s accelerated gradient method: Theory and insights
Su, W., Boyd, S., and Candès, E. J. (2016) · 2016
Solving weakly-convex-weakly-concave saddle-point problems as successive strongly monotone variational inequalities
Lin, Q., Liu, M., Rafique, H., and Yang, T. (2018) · 2018
Later among the works it cites.
Understanding the acceleration phenomenon via high-resolution differential equations
Shi, B., Du, S. S., Jordan, M. I., and Su, W. J. (2018) · 2018
Later among the works it cites.
Local saddle point optimization: A curvature exploitation approach
Adolphs, L., Daneshmand, H., Lucchi, A., and Hofmann, T. (2019) · 2019
Later among the works it cites.
Interaction matters: A note on non-asymptotic local convergence of generative adversarial networks
Liang, T. and Stokes, J. (2019) · 2019
Later among the works it cites.
Solving a class of non-convex min-max games using iterative first order methods
Nouiehed, M., Sanjabi, M., Huang, T., Lee, J. D., and Razaviyayn, M. (2019) · 2019
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Cited alongside, same era.
Generalization and equilibrium in generative adversarial nets (GANs)
Arora, S., Ge, R., Liang, Y., Ma, T., and Zhang, Y. (2017) · 2017
Cited alongside, same era.
The limit points of (optimistic) gradient descent in min-max optimization
Daskalakis, C. and Panageas, I. (2018) · 2018
Cited alongside, same era.
On gradient-based learning in continuous games
Mazumdar, E., Ratliff, L. J., and Sastry, S. S. (2020) · 2020
Closest in time.
Optimality and stability in non-convex smooth games
Zhang, G., Poupart, P., and Yu, Y. (2020) · 2020
Closest in time.