Contextual multinomial logit (MNL) bandits capture many real-world assortment recommendation problems such as online retailing/advertising. However, prior work has only considered (generalized) linear value functions, which greatly limits its applicability. Motivated by this fact, in this work, we consider contextual MNL bandits with a general value function class that contains the ground truth, borrowing ideas from a recent trend of studies on contextual bandits. Specifically, we consider both the stochastic and the adversarial settings, and propose a suite of algorithms, each with different computation-regret trade-off. When applied to the linear case, our results not only are the first ones with no dependence on a certain problem-dependent constant that can be exponentially large, but also enjoy other advantages such as computational efficiency, dimension-free regret bounds, or the ability to handle completely adversarial contexts and rewards.

This paper introduces a novel, integrated approach AHA ( A daptive H uman-A ssisted OOD learning) to simultaneously address both OOD generalization and detection through a human-assisted framework by labeling data in the wild.

Understanding how the collective activity of neural populations relates to computation and ultimately behavior is a key goal in neuroscience.

Despite these advancements, QAOA's practical efficacy is challenged by the quantum coherence limits of modern quantum devices, as there is a ceiling on the allowable maximum circuit depth

Arya et al. suggest using either supervised or self-supervised learning techniques to train the NN; the former requires access to exact inference

In model inversion attacks (MIAs), adversaries attempt to recover the private training data by exploiting access to a well-trained target model.

Vision Transformers (ViTs) are widely used in a variety of applications, while they usually have a fixed architecture that may not match the varying computational resources of different deployment environments.