Search Results for author:
Found 4 papers, 2 papers with code
Beta-VAE Reproducibility: Challenges and Extensions
$\beta$-VAE is a follow-up technique to variational autoencoders that proposes special weighting of the KL divergence term in the VAE loss to obtain disentangled representations.
DARTS without a Validation Set: Optimizing the Marginal Likelihood
The success of neural architecture search (NAS) has historically been limited by excessive compute requirements.
Gold Standard Pairs Trading Rules: Are They Valid?
Pairs trading is a strategy based on exploiting mean reversion in prices of securities.
Speedy Performance Estimation for Neural Architecture Search
Reliable yet efficient evaluation of generalisation performance of a proposed architecture is crucial to the success of neural architecture search (NAS).
Cannot find the paper you are looking for? You can
Submit a new open access paper.
