English
Related papers

Related papers: Conserved active information

200 papers

Active learning algorithms propose which unlabeled objects should be queried for their labels to improve a predictive model the most. We study active learners that minimize generalization bounds and uncover relationships between these…

Machine Learning · Computer Science 2017-06-09 Tom J. Viering , Jesse H. Krijthe , Marco Loog

Recent work studies the supervised online continual learning setting where a learner receives a stream of data whose class distribution changes over time. Distinct from other continual learning settings the learner is presented new samples…

Machine Learning · Computer Science 2022-03-28 Nader Asadi , Sudhir Mudur , Eugene Belilovsky

In-context Learning (ICL) is an emerging few-shot learning paradigm based on modern Language Models (LMs), yet its inner mechanism remains unclear. In this paper, we investigate the mechanism through a novel perspective of information…

Machine Learning · Computer Science 2026-01-29 Hakaze Cho , Haolin Yang , Gouki Minegishi , Naoya Inoue

Active learning aims to optimize the dataset annotation process when resources are constrained. Most existing methods are designed for balanced datasets. Their practical applicability is limited by the fact that a majority of real-life…

Machine Learning · Computer Science 2022-02-02 Umang Aggarwal , Adrian Popescu , Céline Hudelot

We study different aspects of active learning with deep neural networks in a consistent and unified way. i) We investigate incremental and cumulative training modes which specify how the newly labeled data are used for training. ii) We…

Machine Learning · Computer Science 2023-01-02 John Daniel Bossér , Erik Sörstadius , Morteza Haghir Chehreghani

While post-training has successfully improved large language models (LLMs) across a variety of domains, these gains heavily rely on human-labeled data or external verifiers. Existing data has already been exploited, and new data is…

Machine Learning · Computer Science 2026-05-29 Hyunji Nam , Haoran Li , Natasha Jaques

Directed information or its variants are utilized extensively in the characterization of the capacity of channels with memory and feedback, nonanticipative lossy data compression, and their generalizations to networks. In this paper, we…

Information Theory · Computer Science 2015-12-24 Charalambos D. Charalambous , Photios A. Stavrou

We consider sequential search by an agent who cannot observe the quality of goods but can acquire information by buying signals from a profit-maximizing principal with limited commitment power. The principal can charge higher prices for…

Theoretical Economics · Economics 2024-08-13 Teddy Mekonnen , Zeky Murra-Anton , Bobak Pakzad-Hurson

Many active learning methods belong to the retraining-based approaches, which select one unlabeled instance, add it to the training set with its possible labels, retrain the classification model, and evaluate the criteria that we base our…

Machine Learning · Statistics 2017-03-01 Yazhou Yang , Marco Loog

A general framework is introduced to estimate how much external information has been infused into a search algorithm, the so-called active information. This is rephrased as a test of fine-tuning, where tuning corresponds to the amount of…

Statistics Theory · Mathematics 2023-01-26 Daniel Andrés Díaz-Pachón , Ola Hössjer

A stochastic nonlinear dynamical system generates information, as measured by its entropy rate. Some---the ephemeral information---is dissipated and some---the bound information---is actively stored and so affects future behavior. We derive…

Statistical Mechanics · Physics 2015-06-19 Sarah Marzen , James P. Crutchfield

The apparent dichotomy between information-processing and dynamical approaches to complexity science forces researchers to choose between two diverging sets of tools and explanations, creating conflict and often hindering scientific…

Neurons and Cognition · Quantitative Biology 2022-01-26 Pedro A. M. Mediano , Fernando E. Rosas , Juan Carlos Farah , Murray Shanahan , Daniel Bor , Adam B. Barrett

We present a general framework for the information backflow (IB) approach of Markovianity that not only includes a large number, if not all, of IB prescriptions proposed so far but also is equivalent to completely positive divisibility for…

Quantum Physics · Physics 2018-04-03 Sagnik Chakraborty

Large language models (LLMs) exhibit remarkable capabilities in question answering and reasoning thanks to their extensive parametric memory. However, their knowledge is inherently limited by the scope of their pre-training data, while…

Computation and Language · Computer Science 2025-06-10 Atahan Özer , Çağatay Yıldız

Continual learning aims to learn a sequence of tasks by leveraging the knowledge acquired in the past in an online-learning manner while being able to perform well on all previous tasks, this ability is crucial to the artificial…

Computer Vision and Pattern Recognition · Computer Science 2022-09-12 Ya-nan Han , Jian-wei Liu

Weight and activation binarization can efficiently compress deep neural networks and accelerate model inference, but cause severe accuracy degradation. Existing optimization methods for binary neural networks (BNNs) focus on fitting…

Computer Vision and Pattern Recognition · Computer Science 2022-10-07 Ping Xue , Yang Lu , Jingfei Chang , Xing Wei , Zhen Wei

The explosive growth of easily-accessible unlabeled data has lead to growing interest in active learning, a paradigm in which data-hungry learning algorithms adaptively select informative examples in order to lower prohibitively expensive…

Machine Learning · Computer Science 2021-02-11 Max Hopkins , Daniel Kane , Shachar Lovett , Michal Moshkovitz

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

We study the problem of inverse reinforcement learning (IRL), where the learning agent recovers a reward function using expert demonstrations. Most of the existing IRL techniques make the often unrealistic assumption that the agent has…

Machine Learning · Computer Science 2021-12-20 Franck Djeumou , Murat Cubuktepe , Craig Lennon , Ufuk Topcu

Standard computer vision systems assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good observations is a major challenge in itself. We address the problem of learning to…

Computer Vision and Pattern Recognition · Computer Science 2019-06-28 Santhosh K. Ramakrishnan , Dinesh Jayaraman , Kristen Grauman