arXiv Machine Learning June 2, 2026 By Kazuto Fukuchi, Ryuichiro Hataya, Kota Matsui

Provable Data Scaling Law for Meta Learning via Complexity Minimization

Read the original on arXiv Machine Learning →

arXiv:2606. 02008v1 Announce Type: cross Abstract: Pre-training has become a fundamental paradigm in modern machine learning, with one of its key empirical benefits being reduced downstream sample complexity as the scale of pre-training data increases.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers

Jun 1

Provable Data Scaling Law for Meta Learning via Complexity Minimization

Pre-training has become a fundamental paradigm in modern machine learning, with one of its key empirical benefits being reduced downstream sample complexity as the scale of pre-training data increases. However, existing theoretical frameworks for pre-training do not fully explain this phenomenon.

arXiv AI

Jun 2

On the Difficulty of Learning a Meta-network for Training Data Selection

arXiv:2606. 00571v1 Announce Type: cross Abstract: Synthetic data are increasingly used to train neural networks, yet distributional mismatch with real data limits their effectiveness when used indiscriminately.

By Zilin Du, Junqi Zhao, Boyang Albert Li

benchmarks data-engineering

arXiv Machine Learning

Aug 26

TLXML: Task-Level Explanation of Meta-Learning via Influence Functions

arXiv:2501.14271v4 Announce Type: replace Abstract: Meta-learning enables models to rapidly adapt to new tasks by leveraging prior experience, but its adaptation mechanisms remain opaque, especially...

By Yoshihiro Mitsuka, Shadan Golestan, Zahin Sufiyan, Shotaro Miwa, Osmar R. Zaiane

arXiv Machine Learning

Jul 7

Labeled-Data-Free Meta-Learning: Efficient Task Generation Using Pre-trained Models and Unlabeled Data

arXiv:2607. 02850v1 Announce Type: new Abstract: Meta-learning without labeled data is crucial for real-world applications, where obtaining labeled datasets can be expensive or restricted due to privacy concerns.

By Lei Sun, Yusuke Tanaka, Tomoharu Iwata

benchmarks safety

arXiv AI

Jun 4

Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning

arXiv:2605. 23595v2 Announce Type: replace-cross Abstract: The rapid advancement of machine learning has led to an unprecedented expansion of model ecosystems, making it increasingly difficult to assess the reliability of newly released models on unseen and unlabeled data.

By Trinh Pham, Viet Huynh, Hongzhi Yin, Quoc Viet Hung Nguyen, Thanh Tam Nguyen

fine-tuning benchmarks

arXiv Statistics ML

3d ago

Effects of Structural Allocation of Geometric Task Diversity in Linear Meta-Learning Models

arXiv:2509.18349v4 Announce Type: replace Abstract: Meta-learning aims to leverage information across related tasks to improve prediction on unlabeled data for new tasks when only a small number of l...

By Saptati Datta, Nicolas W. Hengartner, Yulia Pimonova, Natalie E. Klein, Nicholas Lubbers

One email a morning, machine-written

Related stories

Provable Data Scaling Law for Meta Learning via Complexity Minimization

On the Difficulty of Learning a Meta-network for Training Data Selection

TLXML: Task-Level Explanation of Meta-Learning via Influence Functions

Labeled-Data-Free Meta-Learning: Efficient Task Generation Using Pre-trained Models and Unlabeled Data

Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning

Effects of Structural Allocation of Geometric Task Diversity in Linear Meta-Learning Models