This paper formulates a framework which unifies several interactive learning problems with a structure such as interactive clustering. Next, the authors show that QBC can be generalized and kernelized to solve the problems in the framework. The consistency and rate of convergence are analyzed. I do not think I could judge the novelty of the theorems and proofs well. Thus, my comments focus on the practicality of the proposed algorithm, which I believe is relevant to its significance and the impact to the field.

Updated Review after Rebuttal: After reading the authors response and re-evaluate the paper I do agree that most of my concerns that there was a fundamental issue with some of their statements were wrong, hence I'm changing my score from 3 to 6. From going into detail of the proof it resides on constructing a generative model where for half of the latent variables (w t z 0) the integral is bounded for all data points and for the other half for 1 data point the integral diverges while for the other goes to zero. This split allows them to say that the one integral diverges and the all of the others are finite hence the likelihood is infinite. However, I'm still not convinced that this issue actually arises at all in practical settings. First, in practice, we are optimizing an ELBO which is never tight, hence for this to be convincing argument the authors should investigate whether there are settings of the ELBO where it diverges except when it can perfectly reconstruct the posterior. Furthermore, I still stand that I do not think that the results on the Frey Faces dataset are interpreted correctly and given that this is a fairly small dataset it is highly likely that the generative model overfits to the data (but not in the way for the divergence to happen). The experimental section in this direction seems to be a bit weak, nevertheless, the paper is worth being accepted.

Existing diffusion-based methods for inverse problems sample from the posterior using score functions and accept the generated random samples as solutions. In applications that posterior mean is preferred, we have to generate multiple samples from the posterior which is time-consuming. In this work, by analyzing the probability density evolution of the conditional reverse diffusion process, we prove that the posterior mean can be achieved by tracking the mean of each reverse diffusion step. Based on that, we establish a framework termed reverse mean propagation (RMP) that targets the posterior mean directly. We show that RMP can be implemented by solving a variational inference problem, which can be further decomposed as minimizing a reverse KL divergence at each reverse step. We further develop an algorithm that optimizes the reverse KL divergence with natural gradient descent using score functions and propagates the mean at each reverse step. Experiments demonstrate the validity of the theory of our framework and show that our algorithm outperforms state-of-the-art algorithms on reconstruction performance with lower computational complexity in various inverse problems.

Recent advances in artificial intelligence have been fueled by the development of foundation models such as BERT, GPT, T5, and Vision Transformers. These models are first pretrained on vast and diverse datasets and then adapted to specific downstream tasks, often with significantly less data. However, the mechanisms behind the success of this ubiquitous pretrain-then-adapt paradigm remain underexplored, particularly the characteristics of pretraining checkpoints that lend themselves to good downstream adaptation. We introduce a Bayesian model selection criterion, called the downstream free energy, which quantifies a checkpoint's adaptability by measuring the concentration of nearby favorable parameters for the downstream task. We demonstrate that this free energy criterion can be effectively implemented without access to the downstream data or prior knowledge of the downstream task. Furthermore, we provide empirical evidence that the free energy criterion reliably correlates with improved fine-tuning performance, offering a principled approach to predicting model adaptability. The advent of foundation models has significantly reshaped the landscape of modern machine learning (Bommasani et al., 2021).

Large language models have demonstrated impressive in-context learning (ICL) capability. However, it is still unclear how the underlying transformers accomplish it, especially in more complex scenarios. Toward this goal, several recent works studied how transformers learn fixed-order Markov chains (FOMC) in context, yet natural languages are more suitably modeled by variable-order Markov chains (VOMC), i.e., context trees (CTs). In this work, we study the ICL of VOMC by viewing language modeling as a form of data compression and focus on small alphabets and low-order VOMCs. This perspective allows us to leverage mature compression algorithms, such as context-tree weighting (CTW) and prediction by partial matching (PPM) algorithms as baselines, the former of which is Bayesian optimal for a class of CTW priors. We empirically observe a few phenomena: 1) Transformers can indeed learn to compress VOMC in-context, while PPM suffers significantly; 2) The performance of transformers is not very sensitive to the number of layers, and even a two-layer transformer can learn in-context quite well; and 3) Transformers trained and tested on non-CTW priors can significantly outperform the CTW algorithm. To explain these phenomena, we analyze the attention map of the transformers and extract two mechanisms, on which we provide two transformer constructions: 1) A construction with $D+2$ layers that can mimic the CTW algorithm accurately for CTs of maximum order $D$, 2) A 2-layer transformer that utilizes the feed-forward network for probability blending. One distinction from the FOMC setting is that a counting mechanism appears to play an important role. We implement these synthetic transformer layers and show that such hybrid transformers can match the ICL performance of transformers, and more interestingly, some of them can perform even better despite the much-reduced parameter sets.

While large language models (LLMs) show impressive decision-making abilities, current methods lack a mechanism for automatic self-improvement from errors during task execution. We propose LEAP, an iterative fine-tuning framework that continually improves LLM agents using feedback from AI expert teachers. Our key insight is to equip the expert teachers with a privileged state -- information that is available during training but hidden at test time. This allows even weak experts to provide precise guidance, significantly improving the student agent's performance without access to privileged information at test time. We evaluate LEAP on diverse decision-making benchmarks, including text-based games (ALFWorld), web navigation (WebShop), and interactive coding (Intercode Bash). Our experiments show that LEAP (1) outperforms behavior cloning and ReAct baselines (2) enables weak student models (e.g., Llama3-8B) to exceed the performance of strong teacher models (GPT4-o), and (3) allows weak models to self-improve using privileged versions of themselves. We also provide a theoretical analysis showing that LEAP's success hinges on balancing privileged information with the student's realizability, which we empirically validate. Our code is available at https://leap-llm.github.io

Biological tree analysis serves as a pivotal tool in uncovering the evolutionary and differentiation relationships among organisms, genes, and cells. Its applications span diverse fields including phylogenetics, developmental biology, ecology, and medicine. Traditional tree inference methods, while foundational in early studies, face increasing limitations in processing the large-scale, complex datasets generated by modern high-throughput technologies. Recent advances in deep learning offer promising solutions, providing enhanced data processing and pattern recognition capabilities. However, challenges remain, particularly in accurately representing the inherently discrete and non-Euclidean nature of biological trees. In this review, we first outline the key biological priors fundamental to phylogenetic and differentiation tree analyses, facilitating a deeper interdisciplinary understanding between deep learning researchers and biologists. We then systematically examine the commonly used data formats and databases, serving as a comprehensive resource for model testing and development. We provide a critical analysis of traditional tree generation methods, exploring their underlying biological assumptions, technical characteristics, and limitations. Current developments in deep learning-based tree generation are reviewed, highlighting both recent advancements and existing challenges. Furthermore, we discuss the diverse applications of biological trees across various biological domains. Finally, we propose potential future directions and trends in leveraging deep learning for biological tree research, aiming to guide further exploration and innovation in this field.

In autonomous driving, accurate motion prediction is essential for safe and efficient motion planning. To ensure safety, planners must rely on reliable uncertainty information about the predicted future behavior of surrounding agents, yet this aspect has received limited attention. This paper addresses the so-far neglected problem of uncertainty modeling in trajectory prediction. We adopt a holistic approach that focuses on uncertainty quantification, decomposition, and the influence of model composition. Our method is based on a theoretically grounded information-theoretic approach to measure uncertainty, allowing us to decompose total uncertainty into its aleatoric and epistemic components. We conduct extensive experiments on the nuScenes dataset to assess how different model architectures and configurations affect uncertainty quantification and model robustness.

Policy evaluation is an important instrument for the comparison of different algorithms in Reinforcement Learning (RL). Yet even a precise knowledge of the value function $V^{\pi}$ corresponding to a policy $\pi$ does not provide reliable information on how far is the policy $\pi$ from the optimal one. We present a novel model-free upper value iteration procedure $({\sf UVIP})$ that allows us to estimate the suboptimality gap $V^{\star}(x) - V^{\pi}(x)$ from above and to construct confidence intervals for $V^\star$. Our approach relies on upper bounds to the solution of the Bellman optimality equation via martingale approach. We provide theoretical guarantees for ${\sf UVIP}$ under general assumptions and illustrate its performance on a number of benchmark RL problems.

Many scientific fields collect longitudinal multivariate count data where the total number of counts is arbitrary (e.g., multinomial observations). These data are often called count compositional as the information in the data relates to the relative frequencies of the categories (Silverman et al., 2018). These data occur frequently in molecular biology (Espinoza et al., 2020), microbiome studies (Silverman et al., 2018; Joseph et al., 2020; Äijö et al., 2018), natural language processing (Linderman et al., 2015), biomedicine (Fokianos and Kedem, 2003), and social sciences (Cargnoni et al., 1997). Although the counting process used to collect these data is often modeled as multinomial, other sources of noise in the system being studied often lead to extra-multinomial variation. While some account for this extra-multinomial variability with multinomial-Dirichlet models (Mosimann, 1962), multinomial logistic-normal models are often superior, as they can account for both positive and negative covariation between multinomial categories (Aitchison and Shen, 1980; Cargnoni et al., 1997; Joseph et al., 2020; Silverman et al., 2018). Moreover, under suitable transformation (i.e., link function), the logistic-normal is multivariate Gaussian.