Pith. sign in

REVIEW 4 cited by

An improvement of the convergence proof of the ADAM-Optimizer

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1804.10587 v1 pith:YZJHZSHA submitted 2018-04-27 cs.LG cs.AIstat.ML

Sebastian Bock , Josef Goppold , Martin Wei{ss} This is my paper · ORCID
classification cs.LGcs.AIstat.ML
keywords proofadam-optimizerconvergenceadaptivegivenimprovementkingmanetworks
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

A common way to train neural networks is the Backpropagation. This algorithm includes a gradient descent method, which needs an adaptive step size. In the area of neural networks, the ADAM-Optimizer is one of the most popular adaptive step size methods. It was invented in \cite{Kingma.2015} by Kingma and Ba. The $5865$ citations in only three years shows additionally the importance of the given paper. We discovered that the given convergence proof of the optimizer contains some mistakes, so that the proof will be wrong. In this paper we give an improvement to the convergence proof of the ADAM-Optimizer.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. DP-MacAdam: Differentially Private Mechanism with Adaptive Clipping and Adaptive Momentum

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    DP-MacAdam combines adaptive clipping and Adam-style momentum in DP-SGD by sharing bias-free empirical gradient statistics, achieving higher utility than DP-SGD, AdaClip, and DP-Adam without manual clipping threshold tuning.

  2. Single-Beat Cuffless Blood Pressure Estimation Using Ear-PPG and ECG with a Lightweight Hybrid Learning Framework

    cs.LG 2026-07 conditional novelty 4.0 of 10

    Ear-PPG plus chest ECG with a lightweight CNN embedding fused to PTT/HRV features yields beat-wise cuffless BP estimates at about 4.0/1.8 mmHg MAE under subject-disjoint tests.

  3. Compute Can't Handle the Truth: Why Communication Tax Prioritizes Memory and Interconnects in Modern AI Infrastructure

    cs.DC 2025-07 reject novelty 4.0 of 10

    A CXL-based disaggregated memory architecture with hybrid XLink interconnects is proposed and prototyped, claiming large speedups for memory-bound AI and HPC workloads.

  4. Deep learning applied to computational mechanics: A comprehensive review, state of the art, and the classics

    cs.LG 2022-12 unverdicted novelty 2.0 of 10

    A comprehensive review of deep learning techniques for computational mechanics, including LSTM for constitutive modeling, PINNs for PDE solving, optimizers, and kernel methods.

Pith tools