paper-with-me

홈 › Papers

Getting Free Bits Back from Rotational Symmetries in LLMs

2024-10-02 · Jiajun He, Gergely Flamich, José Miguel Hernández-Lobato

Current methods for compressing neural network weights, such as decomposition, pruning, quantization, and channel simulation, often overlook the inherent symmetries within these networks and thus waste bits on encoding redundant information. In this paper, we propose a format based on bits-back coding for storing rotationally symmetric Transformer weights more efficiently than the usual array layout at the same floating-point precision. We evaluate our method on Large Language Models (LLMs) pruned by SliceGPT (Ashkboos et al., 2024) and achieve a 3-5% reduction in total bit usage for free across different model sizes and architectures without impacting model performance within a certain numerical precision.

📄 PDF Abstract BibTeX arXiv:2410.01309

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Attention 설명 없음
Adam 설명 없음
Residual Connection 설명 없음
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

Using Machine Learning to Detect Rotational Symmetries from Reflectional Symmetries in 2D Images

2022-01-17 · Koen Ponse, Anna V. Kononova, Maria Loleyt, Bas van Stein

Automated symmetry detection is still a difficult task in 2021. However, it has applications in computer vision, and it also plays an important part in understanding art. This paper focuses on aiding the latter by compar…

BIG-bench Machine LearningSymmetry Detection

Equivariant Representation Learning in the Presence of Stabilizers

2023-01-12 · Luis Armando Pérez Rey, Giovanni Luca Marchetti, Danica Kragic, Dmitri Jarnikov 외

We introduce Equivariant Isomorphic Networks (EquIN) -- a method for learning representations that are equivariant with respect to general group actions over data. Differently from existing equivariant representation lea…

Representation Learning

Symmetry Detection and Classification in Drawings of Graphs

2019-07-01 · Felice De Luca, Md Iqbal Hossain, Stephen Kobourov

Symmetry is a key feature observed in nature (from flowers and leaves, to butterflies and birds) and in human-made objects (from paintings and sculptures, to manufactured objects and architectural design). Rotational, tr…

BIG-bench Machine LearningClassificationGeneral ClassificationSymmetry Detection

Rotationally Equivariant Super-Resolution of Velocity Fields in Two-Dimensional Fluids Using Convolutional Neural Networks

2022-02-22 · Yuki Yasuda, Ryo Onishi

This paper investigates the super-resolution (SR) of velocity fields in two-dimensional fluids from the viewpoint of rotational equivariance. SR refers to techniques that estimate high-resolution images from those in low…

Super-ResolutionTranslation

Lagrangian Neural Network with Differentiable Symmetries and Relational Inductive Bias

2021-10-07 · Ravinder Bhattoo, Sayan Ranu, N. M. Anoop Krishnan

Realistic models of physical world rely on differentiable symmetries that, in turn, correspond to conservation laws. Recent works on Lagrangian and Hamiltonian neural networks show that the underlying symmetries of a sys…

Inductive Bias