Timezone: »

 
Poster
Global Convergence and Variance Reduction for a Class of Nonconvex-Nonconcave Minimax Problems
Junchi Yang · Negar Kiyavash · Niao He

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #816

Nonconvex minimax problems appear frequently in emerging machine learning applications, such as generative adversarial networks and adversarial learning. Simple algorithms such as the gradient descent ascent (GDA) are the common practice for solving these nonconvex games and receive lots of empirical success. Yet, it is known that these vanilla GDA algorithms with constant stepsize can potentially diverge even in the convex setting. In this work, we show that for a subclass of nonconvex-nonconcave objectives satisfying a so-called two-sided Polyak-{\L}ojasiewicz inequality, the alternating gradient descent ascent (AGDA) algorithm converges globally at a linear rate and the stochastic AGDA achieves a sublinear rate. We further develop a variance reduced algorithm that attains a provably faster rate than AGDA when the problem has the finite-sum structure.

Author Information

Junchi Yang (University of Illinois)
Negar Kiyavash (École Polytechnique Fédérale de Lausanne)
Niao He (UIUC)

More from the Same Authors