Knowledge distillation (KD) aims to train a lightweight classifier suitable to provide accurate inference with constrained resources in multi-label learning. Instead of directly consuming feature-label pairs, the classifier is trained by a teacher, i.e., a high-capacity model whose training may be resource-hungry. The accuracy of the classifier trained this way is usually suboptimal because it is difficult to learn the true data distribution from the teacher. An alternative method is to adversarially train the classifier against a discriminator in a two-player game akin to generative adversarial networks (GAN), which can ensure the classifier to learn the true data distribution at the equilibrium of this game. However, it may take excessively long time for such a two-player game to reach equilibrium due to high-variance gradient updates.

Self-play is a technique for machine learning in multi-agent systems where a learning algorithm learns by interacting with copies of itself.

We study the price of anarchy of first-price auctions in the autobidding world, where bidders can be either utility maximizers (i.e., traditional bidders) or value maximizers (i.e., autobidders).

LP-based techniques struggling to scale favorably in large instances.

In this paper, we develop efficient parameterized algorithms for regimes between these two extremes.

The question of "as if" rationality - that is, whether selfishly-minded, myopic agents may learn to

Team-Nash equilibrium (TNE) predicts the outcomes of such coordinated interactions.