Transformer models with the MADL loss are claimed to beat LSTM and buy-and-hold on six assets, but the non-differentiable loss makes the described training impossible.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-fin.CP 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Alternative Loss Function in Evaluation of Transformer Models
Transformer models with the MADL loss are claimed to beat LSTM and buy-and-hold on six assets, but the non-differentiable loss makes the described training impossible.