English
Related papers

Related papers: On-line Learning of an Unlearnable True Teacher th…

200 papers

This paper frames a general prediction system as an observer traveling around a continuous space, measuring values at some locations, and predicting them at others. The observer is completely agnostic about any particular task being solved;…

Neural and Evolutionary Computing · Computer Science 2021-03-24 Elliot Meyerson , Risto Miikkulainen

Continual learning is the problem of learning and retaining knowledge through time over multiple tasks and environments. Research has primarily focused on the incremental classification setting, where new tasks/classes are added at discrete…

Machine Learning · Computer Science 2021-09-23 Zhipeng Cai , Ozan Sener , Vladlen Koltun

In imitation learning, imitators and demonstrators are policies for picking actions given past interactions with the environment. If we run an imitator, we probably want events to unfold similarly to the way they would have if the…

Machine Learning · Computer Science 2022-10-05 Michael K. Cohen , Marcus Hutter , Neel Nanda

A classical learning setting typically concerns an agent/student who collects data, or observations, from a system in order to estimate a certain property of interest. Correctional learning is a type of cooperative teacher-student framework…

Machine Learning · Computer Science 2022-03-30 Inês Lourenço , Rebecka Winqvist , Cristian R. Rojas , Bo Wahlberg

We study the problem of inverse reinforcement learning (IRL) with the added twist that the learner is assisted by a helpful teacher. More formally, we tackle the following algorithmic question: How could a teacher provide an informative…

Machine Learning · Computer Science 2019-06-07 Parameswaran Kamalaruban , Rati Devidze , Volkan Cevher , Adish Singla

Continual learning with an increasing number of classes is a challenging task. The difficulty rises when each example is presented exactly once, which requires the model to learn online. Recent methods with classic parameter optimization…

Machine Learning · Computer Science 2023-08-22 Mateusz Wójcik , Witold Kościukiewicz , Tomasz Kajdanowicz , Adam Gonczarek

Model distillation is an effective and widely used technique to transfer knowledge from a teacher to a student network. The typical application is to transfer from a powerful large network or ensemble to a small network, that is better…

Computer Vision and Pattern Recognition · Computer Science 2017-06-02 Ying Zhang , Tao Xiang , Timothy M. Hospedales , Huchuan Lu

Statistical mechanics is used to study unrealizable generalization in two large feed-forward neural networks with binary weights and output, a perceptron and a tree committee machine. The student is trained by a teacher being larger, i.e.…

Condensed Matter · Physics 2007-05-23 Matts Sporre

We study subliminal learning, a surprising phenomenon where language models transmit behavioral traits via semantically unrelated data. In our main experiments, a "teacher" model with some trait T (such as liking owls or being misaligned)…

Machine Learning · Computer Science 2025-07-22 Alex Cloud , Minh Le , James Chua , Jan Betley , Anna Sztyber-Betley , Jacob Hilton , Samuel Marks , Owain Evans

Offline reinforcement learning learns policies from fixed datasets without further environment interaction. A key challenge in this setting is epistemic uncertainty, arising from limited or biased data coverage, particularly when the…

Machine Learning · Computer Science 2026-04-09 Abhilash Reddy Chenreddy , Erick Delage

Gradient-based meta-learning algorithms have gained popularity for their ability to train models on new tasks using limited data. Empirical observations indicate that such algorithms are able to learn a shared representation across tasks,…

Machine Learning · Computer Science 2025-01-09 Hui Wang , Cho Tung Yip , Bo Li

While deep neural networks can achieve state-of-the-art performance in many tasks, these models are more fragile than they appear. They are prone to learning spurious correlations in their training data, leading to surprising failure cases.…

Machine Learning · Computer Science 2024-09-05 Jeff Mitchell , Jesús Martínez del Rincón , Niall McLaughlin

We study the dynamics of on-line learning in large perceptrons, for the case of training sets with a structural bias of the input vectors, by deriving exact and closed macroscopic dynamical laws using non-equilibrium statistical mechanical…

Disordered Systems and Neural Networks · Physics 2009-10-31 H. C. Rae , J. A. F. Heimel , A. C. C. Coolen

Model smoothing is of central importance for obtaining a reliable teacher model in the student-teacher framework, where the teacher generates surrogate supervision signals to train the student. A popular model smoothing method is the…

Computer Vision and Pattern Recognition · Computer Science 2021-10-05 Tengteng Huang , Yifan Sun , Xun Wang , Haotian Yao , Chi Zhang

We propose an optimization method of mutual learning which converges into the identical state of optimum ensemble learning within the framework of on-line learning, and have analyzed its asymptotic property through the statistical mechanics…

Disordered Systems and Neural Networks · Physics 2015-05-13 Kazuyuki Hara , Takahiro Yamada

Statistical mechanics is used to study unrealizable generalization in two large feed-forward neural networks with binary weights and output, a perceptron and a tree committee machine. The student is trained by a teacher being larger, i.e.…

Condensed Matter · Physics 2007-05-23 Matts Sporre

Observational learning is a type of learning that occurs as a function of observing, retaining and possibly replicating or imitating the behaviour of another agent. It is a core mechanism appearing in various instances of social learning…

Machine Learning · Computer Science 2017-06-22 Diana Borsa , Bilal Piot , Rémi Munos , Olivier Pietquin

The utilization of online stochastic algorithms is popular in large-scale learning settings due to their ability to compute updates on the fly, without the need to store and process data in large batches. When a constant step-size is used,…

Optimization and Control · Mathematics 2023-07-19 Stefan Vlaski , Elsa Rizk , Ali H. Sayed

Unsupervised ensemble learning emerged to address the challenge of combining multiple learners' predictions without access to ground truth labels or additional data. This paradigm is crucial in scenarios where evaluating individual…

Machine Learning · Computer Science 2026-01-29 Ariel Maymon , Yanir Buznah , Uri Shaham

Traditional knowledge distillation transfers "dark knowledge" of a pre-trained teacher network to a student network, and ignores the knowledge in the training process of the teacher, which we call teacher's experience. However, in realistic…

Computer Vision and Pattern Recognition · Computer Science 2022-02-28 Chaofei Wang , Shaowei Zhang , Shiji Song , Gao Huang