We study a new risk-averse bandit setting motivated by semiconductor manufacturing, where the quality of a recipe is judged not by its mean performance but by its weakest outcomes. …
Inspired by recent advances in multi-task bandits, we propose a new problem setting called low-rank, hierarchical Gaussian linear bandits, which combines low-rank structure with …
In reinforcement learning and deep learning, softmax parameterization is commonly used to represent discrete probability distributions.In this work, we study three possible softmax …
We show that a simple trick of randomly corrupting the trajectories in Block MDPs allow for us to use the the clustering algorithm proposed of Jedra et al. (2023) for general …
Linear softmax parametrization (LSP) of a discrete probability distribution is ubiquitous in many areas, such as deep learning, RL, NLP, and social choice models. Instead of trying …
We empirically validate the clustering algorithm proposed in (Jedra et al., 2022).
Inspired from (Wang et al., ICLR'22), we provide a preliminary statistical analysis of stochastic gradient noises (SGNs) of GIN and GCN in Cora node classification task.