English
Related papers

Related papers: When and How Unlabeled Data Provably Improve In-Co…

200 papers

Transformers can perform in-context classification from a few labeled examples, yet the inference-time algorithm remains opaque. We study multi-class linear classification in the hard no-margin regime and make the computation identifiable…

Machine Learning · Computer Science 2026-04-20 Patrick Lutz , Themistoklis Haris , Arjun Chandra , Aditya Gangrade , Venkatesh Saligrama

Pre-trained transformers are able to learn from examples provided as part of the prompt without any weight updates, a remarkable ability known as in-context learning (ICL). Despite its demonstrated efficacy across various domains, the…

Machine Learning · Computer Science 2026-05-07 Alexander Hsu , Zhaiming Shen , Wenjing Liao , Rongjie Lai

In this paper we analyze the graph-based approach to semi-supervised learning under a manifold assumption. We adopt a Bayesian perspective and demonstrate that, for a suitable choice of prior constructed with sufficiently many unlabeled…

Statistics Theory · Mathematics 2021-06-15 Daniel Sanz-Alonso , Ruiyi Yang

In-context learning (ICL) refers to the process of adding a small number of localized examples from a training set of labelled data to an LLM's prompt with an objective to effectively control the generative process seeking to improve the…

Computation and Language · Computer Science 2025-01-22 Manish Chandra , Debasis Ganguly , Iadh Ounis

We demonstrate, theoretically and empirically, that adversarial robustness can significantly benefit from semisupervised learning. Theoretically, we revisit the simple Gaussian model of Schmidt et al. that shows a sample complexity gap…

Machine Learning · Statistics 2022-01-14 Yair Carmon , Aditi Raghunathan , Ludwig Schmidt , Percy Liang , John C. Duchi

Continual Learning (CL) investigates how to train Deep Networks on a stream of tasks without incurring forgetting. CL settings proposed in literature assume that every incoming example is paired with ground-truth annotations. However, this…

Machine Learning · Statistics 2022-08-30 Matteo Boschini , Pietro Buzzega , Lorenzo Bonicelli , Angelo Porrello , Simone Calderara

Active learning typically focuses on training a model on few labeled examples alone, while unlabeled ones are only used for acquisition. In this work we depart from this setting by using both labeled and unlabeled data during model training…

Computer Vision and Pattern Recognition · Computer Science 2019-11-20 Oriane Siméoni , Mateusz Budnik , Yannis Avrithis , Guillaume Gravier

Despite significant advances, the performance of state-of-the-art continual learning approaches hinges on the unrealistic scenario of fully labeled data. In this paper, we tackle this challenge and propose an approach for continual…

Computer Vision and Pattern Recognition · Computer Science 2023-09-12 Zhiqi Kang , Enrico Fini , Moin Nabi , Elisa Ricci , Karteek Alahari

Knowledge distillation with unlabeled examples is a powerful training paradigm for generating compact and lightweight student models in applications where the amount of labeled data is limited but one has access to a large pool of unlabeled…

Machine Learning · Computer Science 2023-06-12 Vasilis Kontonis , Fotis Iliopoulos , Khoa Trinh , Cenk Baykal , Gaurav Menghani , Erik Vee

Transformers have demonstrated a strong ability for in-context learning (ICL), enabling models to solve previously unseen tasks using only example input output pairs provided at inference time. While prior theoretical work has established…

Machine Learning · Computer Science 2026-05-19 Rushil Chandrupatla , Leo Bangayan , Sebastian Leng

We study how in-context learning (ICL) in language models is affected by semantic priors versus input-label mappings. We investigate two setups-ICL with flipped labels and ICL with semantically-unrelated labels-across various model families…

Computation and Language · Computer Science 2023-03-09 Jerry Wei , Jason Wei , Yi Tay , Dustin Tran , Albert Webson , Yifeng Lu , Xinyun Chen , Hanxiao Liu , Da Huang , Denny Zhou , Tengyu Ma

Continual learning aims to learn new tasks incrementally using less computation and memory resources instead of retraining the model from scratch whenever new task arrives. However, existing approaches are designed in supervised fashion…

Computer Vision and Pattern Recognition · Computer Science 2021-08-03 Jiangpeng He , Fengqing Zhu

We investigate the role of various demonstration components in the in-context learning (ICL) performance of large language models (LLMs). Specifically, we explore the impacts of ground-truth labels, input distribution, and complementary…

Computation and Language · Computer Science 2024-04-29 Fuxiao Liu , Paiheng Xu , Zongxia Li , Yue Feng , Hyemi Song

Large language models (LLMs) excel at a range of tasks through in-context learning (ICL), where only a few task examples guide their predictions. However, prior research highlights that LLMs often overlook input-label mapping information in…

Computation and Language · Computer Science 2025-06-10 Keqin Peng , Liang Ding , Yuanxin Ouyang , Meng Fang , Yancheng Yuan , Dacheng Tao

Complementary-label Learning (CLL) is a form of weakly supervised learning that trains an ordinary classifier using only complementary labels, which are the classes that certain instances do not belong to. While existing CLL studies…

Machine Learning · Computer Science 2023-05-16 Wei-I Lin , Gang Niu , Hsuan-Tien Lin , Masashi Sugiyama

In-context learning (ICL), teaching a large language model (LLM) to perform a task with few-shot demonstrations rather than adjusting the model parameters, has emerged as a strong paradigm for using LLMs. While early studies primarily used…

Computation and Language · Computer Science 2023-05-24 Man Luo , Xin Xu , Zhuyun Dai , Panupong Pasupat , Mehran Kazemi , Chitta Baral , Vaiva Imbrasaite , Vincent Y Zhao

The intriguing in-context learning (ICL) abilities of deep Transformer models have lately garnered significant attention. By studying in-context linear regression on unimodal Gaussian data, recent empirical and theoretical works have argued…

Machine Learning · Computer Science 2024-10-30 Khashayar Gatmiry , Nikunj Saunshi , Sashank J. Reddi , Stefanie Jegelka , Sanjiv Kumar

Can in-context learning (ICL) override pre-trained label semantics, or does it merely refine an existing semantic backbone? We address this question by treating LLMs as prompt-induced classifiers and contrasting their behavior under…

Computation and Language · Computer Science 2025-11-27 Anantha Padmanaban Krishna Kumar

Semi-supervised segmentation tackles the scarcity of annotations by leveraging unlabeled data with a small amount of labeled data. A prominent way to utilize the unlabeled data is by consistency training which commonly uses a…

Computer Vision and Pattern Recognition · Computer Science 2022-03-14 Sukesh Adiga , Jose Dolz , Herve Lombaert

In semi-supervised learning for classification, it is assumed that every ground truth class of data is present in the small labelled dataset. Many real-world sparsely-labelled datasets are plausibly not of this type. It could easily be the…

Machine Learning · Statistics 2021-01-11 Matthew Willetts , Stephen J Roberts , Christopher C Holmes
‹ Prev 1 4 5 6 7 8 10 Next ›