Many causal discovery algorithms, including the celebrated FCI algorithm, output a Partial Ancestral Graph (PAG). PAGs serve as an abstract graphical representation of the underlying causal structure, modeled by directed acyclic graphs with latent and selection variables. This paper develops a characterization of the set of extended-type conditional independence relations that are invariant across all causal models represented by a PAG. This theory allows us to formulate a general measure-theoretic version of Pearl's causal calculus and a sound and complete identification algorithm for PAGs under selection bias. Our results also apply when PAGs are learned by certain algorithms that integrate observational data with experimental data and incorporate background knowledge.

Next, we introduce two additional approximations we use to apply Eq. (S.9). An SCM matches a set of assignments to a causal graph. This implies that the error of the approximation Eq. (S.13) is mainly dominated by the gradients of g at hao, and the variance ofnao. Specifically, we use a positive differentiable measure of the statistical dependence, denoted by I. PIDA measures disentanglement of representations for models that are trained from unsupervised data. As a result, we have the following: Minimizing Eq. (S.21) leads topdo(a,o)(ˆφa0) approaching p(ˆφa0|a), which as we have just shown, leads top(ˆφa0|a) approaching pdo(a)(ˆφa0).

Large language models (LLMs) are highly sensitive to their input prompts, making prompt design a central challenge. While automatic prompt optimization (APO) reduces manual engineering, most approaches assume access to ground-truth references such as labeled validation data. In practice, however, collecting high-quality labels is costly and slow. We propose the Prompt Duel Optimizer (PDO), a sample-efficient framework for label-free prompt optimization. PDO formulates the problem as a dueling-bandit setting, where supervision signal comes from pairwise preference feedback provided by an LLM judge. The framework combines Double Thompson Sampling (D-TS), which prioritizes informative prompt comparisons, with Top-Performer Guided Mutation, which expands the candidate pool by mutating high-performing prompts. PDO naturally operates in label-free settings and can also incorporate partial labels to mitigate judge noise. Experiments on BIG-bench Hard (BBH) and MS MARCO show that PDO consistently outperforms baseline methods. Ablation studies further demonstrate the effectiveness of both D-TS and prompt mutation.

By allowing models to predict without task-specific training, in-context learning (ICL) with pretrained LLMs has enormous potential in NLP. However, a number of problems persist in ICL. In particular, its performance is sensitive to the choice and order of in-context examples. Given the same set of in-context examples with different orderings, model performance may vary between near random to near state-of-the-art. In this work, we formulate in-context example ordering as an optimization problem. We examine three problem settings that differ in the assumptions they make about what is known about the task. Inspired by the idea of learning from label proportions, we propose two principles for in-context example ordering guided by model's probability predictions. We apply our proposed principles to thirteen text classification datasets and nine different autoregressive LLMs with 700M to 13B parameters. We demonstrate that our approach outperforms the baselines by improving the classification accuracy, reducing model miscalibration, and also by selecting better in-context examples.

In this paper, we study reinforcement learning (RL) algorithms to solve real-world decision problems with the objective of maximizing the long-term reward as well as satisfying cumulative constraints. We propose a novel first-order policy optimization method, Interior-point Policy Optimization (IPO), which augments the objective with logarithmic barrier functions, inspired by the interior-point method. Our proposed method is easy to implement with performance guarantees and can handle general types of cumulative multi-constraint settings. We conduct extensive evaluations to compare our approach with state-of-the-art baselines. Our algorithm outperforms the baseline algorithms, in terms of reward maximization and constraint satisfaction. Introduction Recent advances have demonstrated significant potentials of deep reinforcement learning (RL) in solving complex sequential decision and control problems, e.g., the Atari game (Mnih et al. 2015), robotics (Andrychowicz et al. 2018), Go (Silver et al. 2016), etc. In such RL problems, the objective is to maximize the discounted cumulative reward. In many other problems, in addition to maximizing the reward, a policy needs to satisfy certain constraints.