MOTPE
Paper Reading Notes: “MOTPE: Multiobjective Tree-Structured Parzen Estimator”
Bayesian Optimization is Superior to Random Search for Machine Learning Hyperparameter Tuning
Paper-reading notes: Bayesian Optimization
Random Search for Hyper-Parameter Optimization
Paper-reading notes: Random Search for Hyper-Parameter Optimization
ALTA: Compiler-Based Analysis of Transformers
Paper-reading notes: ALTA
Tracr: Compiled Transformers as a Laboratory for Interpretability
Paper-reading notes: Tracr
Thinking Like Transformers
Paper-reading notes: RASP
It’s All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization
Paper-reading notes: MIRAS
FNet: Mixing Tokens with Fourier Transforms
Paper-reading notes: FNet
Linformer: Self-Attention with Linear Complexity
Paper-reading notes: Linformer
Rethinking Attention with Performers
Paper-reading notes: Performers