While the approach is presented as a general generative model based on DT and RF, the paper fails to show its practical interest beyond handling missing values at test time. The possibility of using the approach for outlier detection is potentially interesting but the experiment in the paper is restricted to a single dataset and does not include any comparison with competitors except Gaussian KDE. Overall, the properties of GeDT and GeRF as general purpose density estimators are not really studied. My feeling is that because the tree partitioning is unchanged with respect to standard discriminative DT and RF, GeDT and GeRF are probably only appropriate in the context of tasks related to target predictions. In other tasks, I don't see why they would perform better than pure PC models or other methods mentioned in the related work section.

Overall, reviewers found the contribution significantly novel: the authors connect two disjoint domains (decision trees and probabilistic circuits), and demonstrated effectiveness of their approach on datasets with missing values. Two main concerns remain, even after the rebuttal (i) it's unclear how the proposed approach has advantages over existing alternatives (ii) the effect of the hyper-parameters remain unclear. Consensus after the discussion period was to accept.

Strengths: In general, I enjoyed reading this paper. The proposed method capitalizes on employing soft (a.k.a probabilistic) decision trees. However, PDE of each leaf (or region) is computed using non-parametric approach. I liked the idea of directly assigning a probability for the point reaching a particular leaf (region) rather than computing it along the path at each internal node by applying sigmoid like function which is commonly done is soft trees. Moreover, authors did a great job at investigating various aspects of their method.

Summary and Contributions: This paper considers the problem of learning decision trees. You are given samples from a function f on the Boolean cube that is known to be computed by a size s decision tree. The goal is to produce a hypothesis h that is also a small decision tree and is close to f. It was known that simply looking at correlations is not a good idea, simple functions like parity of a few variables would defeat this algorithm. Indeed, I don't think there was any known algorithm that was guaranteed to return a "decision tree" of small size. This paper presents an algorithm of this type.

The three reviews agree that the paper develops strong theoretical results regarding an important topic. Also the techniques are interesting, and the paper is well written. The main negative aspect in the reviews concerns the practical applicability of the results. Although the authors address this in their reply, the reviewers after discussion are not really convinced about the potential for bridging the gap between theory and practice. Regardless of this, the reviewers are clear in their assessment that the work deserves publications purely on the strength of the theoretical contribution.

Weaknesses: - The studied algorithms remain quite far from real random forests (no bootstrap sampling, split choices are fully independent of the data, trees are pruned, etc.) - As in other results in the literature, convergence rates for forests are by-product of convergence rate of individual trees (using Lemma 1). The results therefore do not really show the benefit of using forests instead of trees in terms of convergence rate. This should be discussed in the paper I think. No real conclusion is drawn from the theoretical results that would help better understand standard RF or suggest modification to these methods. I think this kind of very technical contribution would be more appropriate for a journal submission than for a conference (given the limited time allotted for reviewing).

The paper provides finite-sample convergence rates for two simplified variants of random forests. Overall, the contribution is purely theoretical. I personally think that this work shed new interesting ideas on the behavior of a learning algorithm that is intensively used world wide. This work clearly deserve a poster acceptation at NeurIPS.

The setup is original and I see high value in the persistent-noise assumption worked out by the authors. I do have one main question to the authors and while I recommend this paper to be accepted based on significance and appearance of correctness, I do expect a very strong answer on this point for the score to remain high after rebuttal phase. The authors state in their experiment: "To ensure every pair of chemicals can be distinguished, we removed the chemicals that are not identifiable from each other." Well, for significance of the present work, we also need to know how the algorithms are going to behave in the worst-case if there are symmetries and this kind of preprocessing step is omitted. Note that the user would be happy with being presented a set of hypotheses and a certificate that no further test is available to distinguish among them.

All reviewers are positive or very positive about the paper and most reviewers were satisfied by the authors reponse. This is a clear accept. I however encourage the authors to take into account the reviewers comments to improve their paper, especially the (unanswered) issues raised by reviewer 4.

Model monitoring involves analyzing AI algorithms once they have been deployed and detecting changes in their behaviour. This thesis explores machine learning model monitoring ML before the predictions impact real-world decisions or users. This step is characterized by one particular condition: the absence of labelled data at test time, which makes it challenging, even often impossible, to calculate performance metrics. The thesis is structured around two main themes: (i) AI alignment, measuring if AI models behave in a manner consistent with human values and (ii) performance monitoring, measuring if the models achieve specific accuracy goals or desires. The thesis uses a common methodology that unifies all its sections. It explores feature attribution distributions for both monitoring dimensions. Using these feature attribution explanations, we can exploit their theoretical properties to derive and establish certain guarantees and insights into model monitoring.