A pretrained transformer can approximate Lloyd's EM algorithm for multi-class Gaussian clustering and can achieve the minimax optimal clustering error with enough pretraining data.
Transformers learn to implement preconditioned gradient descent for in-context learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Transformers versus the EM Algorithm in Multi-class Clustering
A pretrained transformer can approximate Lloyd's EM algorithm for multi-class Gaussian clustering and can achieve the minimax optimal clustering error with enough pretraining data.