This paper considers the problem of recovering the policies of multiple interacting experts by estimating their reward functions and constraints where the demonstration data of the experts is distributed to a group of learners. We formulate this problem as a distributed bi-level optimization problem and propose a novel bi-level "distributed inverse constrained reinforcement learning" (D-ICRL) algorithm that allows the learners to collaboratively estimate the constraints in the outer loop and learn the corresponding policies and reward functions in the inner loop from the distributed demonstrations through intermittent communications. We formally guarantee that the distributed learners asymptotically achieve consensus which belongs to the set of stationary points of the bi-level optimization problem. Simulations are done to validate the proposed algorithm.

From the problem setting perspective, OOD detection is closely related to neighboring fields including anomaly detection (AD), open set recognition (OSR), and model uncertainty, since methods developed for one domain are often applicable to each other.

The increasing reliance on ML models in high-stakes tasks has raised a major concern about fairness violations.

All relaxations are optimized via our Lagrangian framework. All code was implemented using PyTorch, and optimized using L-BFGS. On the right, the difference framework is used to achieve equality of opportunity on COMP AS. We set the initial learning rate 0.1, which was Here we define equality of opportunity on false negative rates, i.e. predicting that someone Setting s = b, however, causes the linear relaxation to degenerate. For our deep learning experiments, we used the approach of Sec.

Machine learning is also increasingly used by law enforcement, where ethical questions become civil rights questions.

Therefore, it fails to control the false positive rate. Figure 10: Distribution of naive p -value when the null hypothesis is true. Figure 11: Distribution of selective p -value when the null hypothesis is true. Figure 12: Uniform QQ-plot of the pivot. In the above example, we used 3 cuts (pieces) to approximate the function. Figure 13, we show that # encountered intervals still linearly increase in practice. Figure 13: Demonstration of # encountered and # truncation intervals when increasing # cuts (pieces).

Detecting content generated by large language models (LLMs) is crucial for preventing misuse and building trustworthy AI systems. Although existing detection methods perform well, their robustness in out-of-distribution (OOD) scenarios is still lacking. In this paper, we hypothesize that, compared to features used by existing detection methods, the internal representations of LLMs contain more comprehensive and raw features that can more effectively capture and distinguish the statistical pattern differences between LLM-generated texts (LGT) and human-written texts (HWT). We validated this hypothesis across different LLMs and observed significant differences in neural activation patterns when processing these two types of texts. Based on this, we propose RepreGuard, an efficient statistics-based detection method. Specifically, we first employ a surrogate model to collect representation of LGT and HWT, and extract the distinct activation feature that can better identify LGT. We can classify the text by calculating the projection score of the text representations along this feature direction and comparing with a precomputed threshold. Experimental results show that RepreGuard outperforms all baselines with average 94.92% AUROC on both in-distribution (ID) and OOD scenarios, while also demonstrating robust resilience to various text sizes and mainstream attacks. Data and code are publicly available at: https://github.com/NLP2CT/RepreGuard