paper-with-me

홈 › Papers

Understanding Adam Requires Better Rotation Dependent Assumptions

2024-10-25 · Lucas Maes, Tianyue H. Zhang, Alexia Jolicoeur-Martineau, Ioannis Mitliagkas, Damien Scieur, Simon Lacoste-Julien, Charles Guille-Escuret

Despite its widespread adoption, Adam's advantage over Stochastic Gradient Descent (SGD) lacks a comprehensive theoretical explanation. This paper investigates Adam's sensitivity to rotations of the parameter space. We demonstrate that Adam's performance in training transformers degrades under random rotations of the parameter space, indicating a crucial sensitivity to the choice of basis. This reveals that conventional rotation-invariant assumptions are insufficient to capture Adam's advantages theoretically. To better understand the rotation-dependent properties that benefit Adam, we also identify structured rotations that preserve or even enhance its empirical performance. We then examine the rotation-dependent assumptions in the literature, evaluating their adequacy in explaining Adam's behavior across various rotation types. This work highlights the need for new, rotation-dependent theoretical frameworks to fully understand Adam's empirical success in modern machine learning tasks.

📄 PDF Abstract BibTeX arXiv:2410.19964

Code (0)

등록된 구현이 없습니다.

Tasks

Sensitivity

Methods 이 논문이 사용한 방법론

Adam 설명 없음

Similar Papers 제목 키워드 기반

VectorAdam for Rotation Equivariant Geometry Optimization

2022-05-26 · Selena Ling, Nicholas Sharp, Alec Jacobson

The Adam optimization algorithm has proven remarkably effective for optimization problems across machine learning and even traditional tasks in geometry processing. At the same time, the development of equivariant method…

BIG-bench Machine Learning

ButterflyQuant: Ultra-low-bit LLM Quantization through Learnable Orthogonal Butterfly Transforms

2025-09-11 · Bingxin Xu, Zhen Dong, Oussama Elachqar, Yuzhang Shang arxiv

Large language models require massive memory footprints, severely limiting deployment on consumer hardware. Quantization reduces memory through lower numerical precision, but extreme 2-bit quantization suffers from catas…

How do simple rotations affect the implicit bias of Adam?

2025-10-27 · Adela DePavia, Vasileios Charisopoulos, Rebecca Willett arxiv

Adaptive gradient methods such as Adam and Adagrad are widely used in machine learning, yet their effect on the generalization of learned models -- relative to methods like gradient descent -- remains poorly understood. …

Binary Classification

OptRot: Mitigating Weight Outliers via Data-Free Rotations for Post-Training Quantization

2025-12-30 · Advait Gadhikar, Riccardo Grazzi, James Hensman arxiv

The presence of outliers in Large Language Models (LLMs) weights and activations makes them difficult to quantize. Recent work has leveraged rotations to mitigate these outliers. In this work, we propose methods that lea…

Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks

2023-05-26 · Atli Kosson, Bettina Messmer, Martin Jaggi

This study investigates how weight decay affects the update behavior of individual neurons in deep neural networks through a combination of applied analysis and experimentation. Weight decay can cause the expected magnit…

L2 Regularization