A central goal of both knowledge tracing and traditional assessment is to quantify student knowledge and skills at a given point in time. Deep knowledge tracing flexibly considers a student's response history but does not quantify epistemic uncertainty, while IRT and CDM compute measurement error but only consider responses to individual tests in isolation from a student's past responses. Elo and BKT could bridge this divide, but the simplicity of the underlying models limits information sharing across skills and imposes strong inductive biases. To overcome these limitations, we introduce Dynamic LENS, a modeling paradigm that combines the flexible uncertainty-preserving properties of variational autoencoders with the principled information integration of Bayesian state-space models. Dynamic LENS allows information from student responses to be collected across time, while treating responses from the same test as exchangeable observations generated by a shared latent state. It represents student knowledge as Gaussian distributions in high-dimensional space and combines estimates both within tests and across time using Bayesian updating. We show that Dynamic LENS has similar predictive performance to competing models, while preserving the epistemic uncertainty - the deep learning analogue to measurement error - that DKT models lack. This approach provides a conceptual bridge across an important divide between models designed for formative practice and summative assessment.

This paper introduces factored conditional filters, new filtering algorithms for simultaneously tracking states and estimating parameters in high-dimensional state spaces. The conditional nature of the algorithms is used to estimate parameters and the factored nature is used to decompose the state space into low-dimensional subspaces in such a way that filtering on these subspaces gives distributions whose product is a good approximation to the distribution on the entire state space. The conditions for successful application of the algorithms are that observations be available at the subspace level and that the transition model can be factored into local transition models that are approximately confined to the subspaces; these conditions are widely satisfied in computer science, engineering, and geophysical filtering applications. We give experimental results on tracking epidemics and estimating parameters in large contact networks that show the effectiveness of our approach.

Markov Decision Process (MDP) is a common mathematical model for sequential decision-making problems. In this paper, we present a new geometric interpretation of MDP, which is useful for analyzing the dynamics of main MDP algorithms. Based on this interpretation, we demonstrate that MDPs can be split into equivalence classes with indistinguishable algorithm dynamics. The related normalization procedure allows for the design of a new class of MDP-solving algorithms that find optimal policies without computing policy values.

Reinforcement learning from human feedback (RLHF) provides a principled framework for aligning AI systems with human preference data. For various reasons, e.g., personal bias, context ambiguity, lack of training, etc, human annotators may give incorrect or inconsistent preference labels. To tackle this challenge, we propose a robust RLHF approach -- $R^3M$, which models the potentially corrupted preference label as sparse outliers. Accordingly, we formulate the robust reward learning as an $\ell_1$-regularized maximum likelihood estimation problem. Computationally, we develop an efficient alternating optimization algorithm, which only incurs negligible computational overhead compared with the standard RLHF approach. Theoretically, we prove that under proper regularity conditions, $R^3M$ can consistently learn the underlying reward and identify outliers, provided that the number of outlier labels scales sublinearly with the preference sample size. Furthermore, we remark that $R^3M$ is versatile and can be extended to various preference optimization methods, including direct preference optimization (DPO). Our experiments on robotic control and natural language generation with large language models (LLMs) show that $R^3M$ improves robustness of the reward against several types of perturbations to the preference data.

Multi-label ranking, which returns multiple top-ranked labels for each instance, has a wide range of applications for visual tasks. Due to its complicated setting, prior arts have proposed various measures to evaluate model performances. However, both theoretical analysis and empirical observations show that a model might perform inconsistently on different measures. To bridge this gap, this paper proposes a novel measure named Top-K Pairwise Ranking (TKPR), and a series of analyses show that TKPR is compatible with existing ranking-based measures. In light of this, we further establish an empirical surrogate risk minimization framework for TKPR. On one hand, the proposed framework enjoys convex surrogate losses with the theoretical support of Fisher consistency. On the other hand, we establish a sharp generalization bound for the proposed framework based on a novel technique named data-dependent contraction. Finally, empirical results on benchmark datasets validate the effectiveness of the proposed framework.

One of the primary catalysts fueling advances in artificial intelligence (AI) and machine learning (ML) is the availability of massive, curated datasets. A commonly used technique to curate such massive datasets is crowdsourcing, where data are dispatched to multiple annotators. The annotator-produced labels are then fused to serve downstream learning and inference tasks. This annotation process often creates noisy labels due to various reasons, such as the limited expertise, or unreliability of annotators, among others. Therefore, a core objective in crowdsourcing is to develop methods that effectively mitigate the negative impact of such label noise on learning tasks. This feature article introduces advances in learning from noisy crowdsourced labels. The focus is on key crowdsourcing models and their methodological treatments, from classical statistical models to recent deep learning-based approaches, emphasizing analytical insights and algorithmic developments. In particular, this article reviews the connections between signal processing (SP) theory and methods, such as identifiability of tensor and nonnegative matrix factorization, and novel, principled solutions of longstanding challenges in crowdsourcing -- showing how SP perspectives drive the advancements of this field. Furthermore, this article touches upon emerging topics that are critical for developing cutting-edge AI/ML systems, such as crowdsourcing in reinforcement learning with human feedback (RLHF) and direct preference optimization (DPO) that are key techniques for fine-tuning large language models (LLMs).

The proliferation of unmanned aerial vehicles (UAVs) in controlled airspace presents significant risks, including potential collisions, disruptions to air traffic, and security threats. Ensuring the safe and efficient operation of airspace, particularly in urban environments and near critical infrastructure, necessitates effective methods to intercept unauthorized or non-cooperative UAVs. This work addresses the critical need for robust, adaptive systems capable of managing such threats through the use of Reinforcement Learning (RL). We present a novel approach utilizing RL to train fixed-wing UAV pursuer agents for intercepting dynamic evader targets. Our methodology explores both model-based and model-free RL algorithms, specifically DreamerV3, Truncated Quantile Critics (TQC), and Soft Actor-Critic (SAC). The training and evaluation of these algorithms were conducted under diverse scenarios, including unseen evasion strategies and environmental perturbations. Our approach leverages high-fidelity flight dynamics simulations to create realistic training environments. This research underscores the importance of developing intelligent, adaptive control systems for UAV interception, significantly contributing to the advancement of secure and efficient airspace management. It demonstrates the potential of RL to train systems capable of autonomously achieving these critical tasks.

Tackling the problem of learning probabilistic classifiers from incomplete data in the context of Knowledge Graphs expressed in Description Logics, we describe an inductive approach based on learning simple belief networks. Specifically, we consider a basic probabilistic model, a Naive Bayes classifier, based on multivariate Bernoullis and its extension to a two-tier network in which this classification model is connected to a lower layer consisting of a mixture of Bernoullis. We show how such models can be converted into (probabilistic) axioms (or rules) thus ensuring more interpretability. Moreover they may be also initialized exploiting expert knowledge. We present and discuss the outcomes of an empirical evaluation which aimed at testing the effectiveness of the models on a number of random classification problems with different ontologies.

We consider (stochastic) softmax policy gradient (PG) methods for bandits and tabular Markov decision processes (MDPs). While the PG objective is non-concave, recent research has used the objective's smoothness and gradient domination properties to achieve convergence to an optimal policy. However, these theoretical results require setting the algorithm parameters according to unknown problem-dependent quantities (e.g. the optimal action or the true reward vector in a bandit problem). To address this issue, we borrow ideas from the optimization literature to design practical, principled PG methods in both the exact and stochastic settings. In the exact setting, we employ an Armijo line-search to set the step-size for softmax PG and demonstrate a linear convergence rate. In the stochastic setting, we utilize exponentially decreasing step-sizes, and characterize the convergence rate of the resulting algorithm. We show that the proposed algorithm offers similar theoretical guarantees as the state-of-the art results, but does not require the knowledge of oracle-like quantities. For the multi-armed bandit setting, our techniques result in a theoretically-principled PG algorithm that does not require explicit exploration, the knowledge of the reward gap, the reward distributions, or the noise. Finally, we empirically compare the proposed methods to PG approaches that require oracle knowledge, and demonstrate competitive performance.

With the development of Human-AI Collaboration in Classification (HAI-CC), integrating users and AI predictions becomes challenging due to the complex decision-making process. This process has three options: 1) AI autonomously classifies, 2) learning to complement, where AI collaborates with users, and 3) learning to defer, where AI defers to users. Despite their interconnected nature, these options have been studied in isolation rather than as components of a unified system. In this paper, we address this weakness with the novel HAI-CC methodology, called Learning to Complement and to Defer to Multiple Users (LECODU). LECODU not only combines learning to complement and learning to defer strategies, but it also incorporates an estimation of the optimal number of users to engage in the decision process. The training of LECODU maximises classification accuracy and minimises collaboration costs associated with user involvement. Comprehensive evaluations across real-world and synthesized datasets demonstrate LECODU's superior performance compared to state-of-the-art HAI-CC methods. Remarkably, even when relying on unreliable users with high rates of label noise, LECODU exhibits significant improvement over both human decision-makers alone and AI alone.