paper-with-me

홈 › Papers

Unify Variables in Neural Scaling Laws for General Audio Representations via Embedding Effective Rank

2025-10-13 · Xuyao Deng, Yanjie Sun, Yong Dou, Kele Xu arxiv

Scaling laws have profoundly shaped our understanding of model performance in computer vision and natural language processing, yet their application to general audio representation learning remains underexplored. A key challenge lies in the multifactorial nature of general audio representation-representation quality is jointly influenced by variables such as audio length, embedding dimensionality, model depth, model architecture, data volume, etc., many of which are difficult to isolate or express analytically. In this work, we present a systematic study of scaling laws for general audio representations by utilizing embedding effective rank (RankMe) as a unifying metric that encapsulates the impact of diverse variables on representation quality. RankMe enables a label-free, information-theoretic quantification of audio embeddings, allowing us to examine scaling behaviors across a wide hyper-parameter space, including model size, training data volume, computational budget, architectural configurations, etc. Our empirical findings reveal a consistent power-law relationship between RankMe and representation quality, suggesting that embedding effective rank serves as a reliable proxy for assessing and predicting model performance in audio representation learning. This work not only validates the applicability of classical scaling principles to the general audio domain but also offers a theoretically grounded and empirically robust framework for guiding future model scaling strategies in audio foundation models.

📄 PDF Abstract BibTeX arXiv:2510.10948

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

Unifying Two Types of Scaling Laws from the Perspective of Conditional Kolmogorov Complexity

2025-01-12 · Jun Wan

In 2020, OpenAI proposed the first type of Scaling Laws, describing the relationships between model performance and parameters, data, and compute. In 2024, OpenAI proposed the second type of Scaling Laws, describing the …

Neural Scaling Laws Rooted in the Data Distribution

2024-12-10 · Ari Brill

Deep neural networks exhibit empirical neural scaling laws, with error decreasing as a power law with increasing model or data size, across a wide variety of architectures, tasks, and datasets. This universality suggests…

Language ModelingLanguage Modelling

Scaling Laws are Redundancy Laws

2025-09-25 · Yuda Bi, Vince D Calhoun arxiv

Scaling laws, a defining feature of deep learning, reveal a striking power-law improvement in model performance with increasing dataset and model size. Yet, their mathematical origins, especially the scaling exponent, ha…

Effective Frontiers: A Unification of Neural Scaling Laws

2026-02-01 · Jiaxuan Zou, Zixuan Gong, Ye Su, Huayi Tang 외 arxiv

Neural scaling laws govern the prediction power-law improvement of test loss with respect to model capacity ($N$), datasize ($D$), and compute ($C$). However, existing theoretical explanations often rely on specific arch…

Scaling Laws for Precision

2024-11-07 · Tanishq Kumar, Zachary Ankner, Benjamin F. Spector, Blake Bordelon 외

Low precision training and inference affect both the quality and cost of language models, but current scaling laws do not account for this. In this work, we devise "precision-aware" scaling laws for both training and inf…

Quantization