Related papers: Conditional Teacher-Student Learning
Language models exhibit an emergent ability to learn a new task from a small number of input-output demonstrations. However, recent work shows that in-context learners largely rely on their pre-trained knowledge, such as the sentiment of…
At the core of self-supervised learning for vision is the idea of learning invariant or equivariant representations with respect to a set of data transformations. This approach, however, introduces strong inductive biases, which can render…
We address the challenge of learning safe and robust decision policies in presence of uncertainty in context of the real scientific problem of adaptive resource oversubscription to enhance resource efficiency while ensuring safety against…
Although reinforcement learning (RL) can provide reliable solutions in many settings, practitioners are often wary of the discrepancies between the RL solution and their status quo procedures. Therefore, they may be reluctant to adapt to…
Mainstream approaches to aligning large language models (LLMs) heavily rely on human preference data, particularly when models require periodic updates. The standard process for iterative alignment of LLMs involves collecting new human…
Intelligent tutoring systems optimize the selection and timing of learning materials to enhance understanding and long-term retention. This requires estimates of both the learner's progress (''knowledge tracing''; KT), and the prerequisite…
Imitation learning is an approach in which an agent learns how to execute a task by trying to mimic how one or more teachers perform it. This learning approach offers a compromise between the time it takes to learn a new task and the effort…
Data driven models of dynamical systems help planners and controllers to provide more precise and accurate motions. Most model learning algorithms will try to minimize a loss function between the observed data and the model's predictions.…
Methods of transfer learning try to combine knowledge from several related tasks (or domains) to improve performance on a test task. Inspired by causal methodology, we relax the usual covariate shift assumption and assume that it holds true…
Knowledge distillation leverages a teacher model to improve the training of a student model. A persistent challenge is that a better teacher does not always yield a better student, to which a common mitigation is to use additional…
Recent advancements in unsupervised domain adaptation (UDA) and semi-supervised learning (SSL), particularly incorporating causality, have led to significant methodological improvements in these learning problems. However, a formal theory…
Learned dynamics models combined with both planning and policy learning algorithms have shown promise in enabling artificial agents to learn to perform many diverse tasks with limited supervision. However, one of the fundamental challenges…
Learning from rewards (i.e., reinforcement learning or RL) and learning to imitate a teacher (i.e., teacher-student learning) are two established approaches for solving sequential decision-making problems. To combine the benefits of these…
Multi-step ahead prediction in language models is challenging due to the discrepancy between training and test time processes. At test time, a sequence predictor is required to make predictions given past predictions as the input, instead…
In computer simulation of the learning process is usually assumed that all elements of the training material are assimilated equally durable. But in practice, the knowledge, which a student uses in its operations, are remembered much…
Safe reinforcement learning (RL) agents accomplish given tasks while adhering to specific constraints. Employing constraints expressed via easily-understandable human language offers considerable potential for real-world applications due to…
Time-series representation learning can extract representations from data with temporal dynamics and sparse labels. When labeled data are sparse but unlabeled data are abundant, contrastive learning, i.e., a framework to learn a latent…
Rich sources of variability in natural speech present significant challenges to current data intensive speech recognition technologies. To model both speaker and environment level diversity, this paper proposes a novel Bayesian factorised…
Semi-supervised domain adaptation (SSDA) is to adapt a learner to a new domain with only a small set of labeled samples when a large labeled dataset is given on a source domain. In this paper, we propose a pair-based SSDA method that adapts…
Object detectors often suffer from the domain gap between training (source domain) and real-world applications (target domain). Mean-teacher self-training is a powerful paradigm in unsupervised domain adaptation for object detection, but it…