paper-with-me

Papers

The Mathematical Relationship Between Layer Normalization and Dynamic Activation Functions

2025-03-27 · Felix Stollenwerk

A recent paper proposes Dynamic Tanh (DyT) as a drop-in replacement for layer normalization (LN). Although the method is empirically well-motivated and appealing from a practical point of view, it lacks a theoretical foundation. In this work, we shed light on the mathematical relationship between layer normalization and dynamic activation functions. In particular, we derive DyT from LN and show that a well-defined approximation is needed to do so. By dropping said approximation, an alternative activation function is obtained, which we call Dynamic Inverse Square Root Unit (DyISRU). DyISRU is the exact counterpart of layer normalization, and we demonstrate numerically that it indeed resembles LN more accurately than DyT does.

📄 PDF Abstract BibTeX arXiv:2503.21708

Code (2)

flxst/ELN 공식 구현
flxst/dynamic-activation-functions 공식 구현

Methods 이 논문이 사용한 방법론

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

Evolving Normalization-Activation Layers

2020-04-06 · NeurIPS 2020 12 · Hanxiao Liu, Andrew Brock, Karen Simonyan, Quoc V. Le

Normalization layers and activation functions are fundamental components in deep networks and typically co-locate with each other. Here we propose to design them using an automated approach. Instead of designing them sep…

image-classificationImage ClassificationImage GenerationInstance Segmentation+1

Discrete Semantic States and Hamiltonian Dynamics in LLM Embedding Spaces

2025-12-29 · Timo Aukusti Laine arxiv

We investigate the structure of Large Language Model (LLM) embedding spaces using mathematical concepts, particularly linear algebra and the Hamiltonian formalism, drawing inspiration from analogies with quantum mechanic…

Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction

2022-06-14 · Kaifeng Lyu, Zhiyuan Li, Sanjeev Arora

Normalization layers (e.g., Batch Normalization, Layer Normalization) were introduced to help with optimization difficulties in very deep nets, but they clearly also help generalization, even in not-so-deep nets. Motivat…

Clustering in pure-attention hardmax transformers and its role in sentiment analysis

2024-06-26 · Albert Alcalde, Giovanni Fantuzzi, Enrique Zuazua

Transformers are extremely successful machine learning models whose mathematical properties remain poorly understood. Here, we rigorously characterize the behavior of transformers with hardmax self-attention and normaliz…

Sentiment Analysis

Dynamic Group Normalization: Spatio-Temporal Adaptation to Evolving Data Statistics

2025-01-01 · CVPR 2025 1 · Yair Smadar, Assaf Hoogi

Deep neural networks remain vulnerable to statistical variations in data, even with advances in normalization techniques. Existing methods use fixed-size normalization sets, restricting their adaptability to evolving…

Computational EfficiencyOut-of-Distribution Generalization