Country
Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds Jiayi Huang 1 Han Zhong 1 Liwei Wang
Our contributions are summarized as follows.
TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-cases
We evaluated adversarial robustness with CAA, an ensemble of gradient and search attacks which was recently demonstrated as the most effective attack against a tabular model.
Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning Tyler Kastner
We consider the problem of learning models for risk-sensitive reinforcement learning.
One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detection
Traditional Anomaly Detection (AD) methods have predominantly relied on unsupervised learning from extensive normal data.
Understanding Transformer Reasoning Capabilities via Graph Algorithms Clayton Sanford
Which transformer scaling regimes are able to perfectly solve different classes of algorithmic problems?
