On the Convergence of Encoder-only Shallow Transformers.
Yongtao WuFanghui LiuGrigorios ChrysosVolkan CevherPublished in: NeurIPS (2023)
Keyphrases
- natural language processing
- bit rate
- convergence speed
- database
- rate distortion
- convergence rate
- iterative algorithms
- initial conditions
- video compression
- video coding
- low complexity
- wyner ziv video coding
- power reduction
- question answering
- motion estimation
- information extraction
- artificial intelligence
- genetic algorithm