Adam: A Method for Stochastic Optimization

Diederik P. Kingma, Jimmy Ba

Published May 2015 · ICLR 2015 (3rd International Conference on Learning Representations) · Conference paper

Summary

This paper introduced Adam, a first-order gradient-based optimization algorithm for stochastic objective functions that computes adaptive per-parameter learning rates from estimates of the first and second moments of the gradients. The method is computationally efficient, has low memory requirements, and is well suited to large-scale and noisy/sparse-gradient problems. It became one of the most widely used optimizers in deep learning.

Key findings

Proposed an adaptive optimizer combining momentum (first moment) and RMSProp-style second-moment scaling with bias correction.
Requires little tuning and works well across a wide range of machine learning problems.
Provided convergence analysis and empirical results showing favorable performance versus other optimizers.

Subjects & keywords

Artificial Intelligence optimization stochastic gradient descent deep learning adaptive learning rate

Cite this paper

APA

Diederik P. Kingma, & Jimmy Ba (2015). Adam: A Method for Stochastic Optimization. ICLR 2015 (3rd International Conference on Learning Representations). https://arxiv.org/abs/1412.6980

BibTeX

@inproceedings{kingma2015adam,
  author    = {Diederik P. Kingma and Jimmy Ba},
  title     = {Adam: A Method for Stochastic Optimization},
  booktitle = {ICLR 2015 (3rd International Conference on Learning Representations)},
  year      = {2015},
  url       = {https://arxiv.org/abs/1412.6980}
}

Related in Artificial Intelligence

AI2023

Segment Anything

Alexander Kirillov, Eric Mintun and Nikhila Ravi

This paper introduces the Segment Anything project: a promptable image segmentation task, the Segment Anything Model (SAM), and the SA-1B dataset. SAM combines an image encoder, a flexible prompt encoder (points, boxes, masks, text), and a fast mask decoder to produce valid segmentation masks from arbitrary prompts. Trained on over 1 billion masks across 11 million images, SAM shows strong zero-shot transfer to many segmentation tasks without additional training.

IEEE/CVF International Conference on Computer Vision (ICCV) Open access

AI2023

GPT-4 Technical Report

OpenAI

This technical report describes GPT-4, a large-scale multimodal Transformer model that accepts image and text inputs and produces text outputs. The report emphasizes that GPT-4 achieves human-level performance on a range of professional and academic benchmarks, and details infrastructure and optimization methods that allowed performance to be predicted from much smaller models. For competitive and safety reasons, the report withholds architecture, dataset, and training details.

arXiv Open access

AI2023

LLaMA: Open and Efficient Foundation Language Models

Hugo Touvron, Thibaut Lavril and Gautier Izacard

The paper presents LLaMA, a family of foundation language models ranging from 7B to 65B parameters trained exclusively on publicly available datasets. It argues that strong performance can be reached without proprietary data and at smaller parameter counts than prior models. LLaMA-13B outperforms the much larger GPT-3 175B on most benchmarks, and LLaMA-65B is competitive with the best contemporary models such as Chinchilla-70B and PaLM-540B.

arXiv preprint (arXiv:2302.13971) Open access