paper-with-me

홈 › Papers

Improved Scaling Laws via Weak-to-Strong Generalization in Random Feature Ridge Regression

2026-03-05 · Diyuan Wu, Lehan Chen, Theodor Misiakiewicz, Marco Mondelli arxiv

It is increasingly common in machine learning to use learned models to label data and then employ such data to train more capable models. The phenomenon of weak-to-strong generalization exemplifies the advantage of this two-stage procedure: a strong student is trained on imperfect labels obtained from a weak teacher, and yet the strong student outperforms the weak teacher. In this paper, we show that the potential improvement is substantial, in the sense that it affects the scaling law followed by the test error. Specifically, we consider students and teachers trained via random feature ridge regression (RFRR). Our main technical contribution is to derive a deterministic equivalent for the excess test error of the student trained on labels obtained via the teacher. Via this deterministic equivalent, we then identify regimes in which the scaling law of the student improves upon that of the teacher, unveiling that the improvement can be achieved both in bias-dominated and variance-dominated settings. Strikingly, the student may attain the minimax optimal rate regardless of the scaling law of the teacher -- in fact, when the test error of the teacher does not even decay with the sample size.

📄 PDF Abstract BibTeX arXiv:2603.05691

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws

2024-10-24 · M. Emrullah Ildiz, Halil Alperen Gozeten, Ege Onur Taga, Marco Mondelli 외

A growing number of machine learning scenarios rely on knowledge distillation where one uses the output of a surrogate model as labels to supervise the training of a target model. In this work, we provide a sharp charact…

Knowledge Distillationregression

Scaling Laws from Sequential Feature Recovery: A Solvable Hierarchical Model

2026-05-14 · Arie Wortsman-Zurich, Hugo Tabanelli, Yatin Dandi, Florent Krzakala 외 arxiv

We propose a simple mechanism by which scaling laws emerge from feature learning in multi-layer networks. We study a high-dimensional hierarchical target that is a globally high-degree function, but that can be represent…

Contrastive Weak-to-strong Generalization

2025-10-09 · Houcheng Jiang, Junfeng Fang, Jiaxin Wu, Tianyu Zhang 외 arxiv

Weak-to-strong generalization provides a promising paradigm for scaling large language models (LLMs) by training stronger models on samples from aligned weaker ones, without requiring human feedback or explicit reward mo…

Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo

2025-03-12 · Zachary Charles, Gabriel Teston, Lucio Dery, Keith Rush 외

As we scale to more massive machine learning models, the frequent synchronization demands inherent in data-parallel approaches create significant slowdowns, posing a critical challenge to further scaling. Recent work dev…

Language ModelingLanguage Modelling

A Theory for Emergence of Complex Skills in Language Models

2023-07-29 · Sanjeev Arora, Anirudh Goyal

A major driver of AI products today is the fact that new skills emerge in language models when their parameter set and training corpora are scaled up. This phenomenon is poorly understood, and a mechanistic explanation v…

Inductive Bias