A Theory on Adam Instability in Large-Scale Machine Learning.
Igor MolybogPeter AlbertMoya ChenZachary DeVitoDavid EsiobuNaman GoyalPunit Singh KouraSharan NarangAndrew PoultonRuan SilvaBinh TangPuxin XuYuchen ZhangMelanie KambadurStephen RollerSusan ZhangPublished in: CoRR (2023)
Keyphrases
- machine learning
- learning algorithm
- database
- learning tasks
- real world
- learning systems
- machine learning algorithms
- theoretical framework
- pattern recognition
- decision trees
- natural language
- computer science
- real life
- supervised learning
- computational model
- explanation based learning
- statistical learning theory
- formal theory
- knowledge acquisition
- computational intelligence
- text mining
- natural language processing
- bayesian networks
- artificial intelligence