paper-with-me

홈 › Papers

On a Conjecture Regarding the Adam Optimizer

2021-11-16 · Mohamed Akrout, Douglas Tweed

Why does the Adam optimizer work so well in deep-learning applications? Adam's originators, Kingma and Ba, presented a mathematical argument that was meant to help explain its success, but Bock and colleagues have since reported that a key piece is missing from that argument $-$ an unproven lemma which we will call Bock's conjecture. Here we show that this conjecture is false, but we prove a modified version of it $-$ a generalization of a result of Reddi and colleagues $-$ which can take its place in analyses of Adam.

📄 PDF Abstract BibTeX arXiv:2111.08162

Code (0)

등록된 구현이 없습니다.

Tasks

LEMMA

Methods 이 논문이 사용한 방법론

Adam 설명 없음

Similar Papers 제목 키워드 기반

Exact Risk Curves of signSGD in High-Dimensions: Quantifying Preconditioning and Noise-Compression Effects

2024-11-19 · Ke Liang Xiao, Noah Marshall, Atish Agarwala, Elliot Paquette

In recent years, signSGD has garnered interest as both a practical optimizer as well as a simple model to understand adaptive optimizers like Adam. Though there is a general consensus that signSGD acts to precondition op…

The Implicit Bias of Adam on Separable Data

2024-06-15 · Chenyang Zhang, Difan Zou, Yuan Cao

Adam has become one of the most favored optimizers in deep learning problems. Despite its success in practice, numerous mysteries persist regarding its theoretical understanding. In this paper, we study the implicit bias…

On the Convergence of Adam under Non-uniform Smoothness: Separability from SGDM and Beyond

2024-03-22 · Bohan Wang, Huishuai Zhang, Qi Meng, Ruoyu Sun 외

This paper aims to clearly distinguish between Stochastic Gradient Descent with Momentum (SGDM) and Adam in terms of their convergence rates. We demonstrate that Adam achieves a faster convergence compared to SGDM under …

DP-AdamW: Investigating Decoupled Weight Decay and Bias Correction in Private Deep Learning

2025-11-11 · Jay Chooi, Kevin Cong, Russell Li, Lillian Sun arxiv

As deep learning methods increasingly utilize sensitive data on a widespread scale, differential privacy (DP) offers formal guarantees to protect against information leakage during model training. A significant challenge…

Image ClassificationNode ClassificationText Classification

An Isometric Stochastic Optimizer

2023-07-24 · Jacob Jackson

The Adam optimizer is the standard choice in deep learning applications. I propose a simple explanation of Adam's success: it makes each parameter's step size independent of the norms of the other parameters. Based on th…