2 papers
cs.LG2026
The RNN Homunculus: Learning to Gate Long-Term Memory
Zeyu Fan, Alexandru-Dragos Manolache, Jan van Gemert
Learning long-range dependencies with recurrent neural networks (RNNs) is difficult because of the vanishing gradient problem. Gated recurrent neural networks like GRUs and LSTMs a…
econ.GN2026
Dynamics of the Currency Composition of Central Bank Reserves
Deborah Gefang, Stephen G. Hall, George S. Tavlas
We examine how macroeconomic and geopolitical developments in the United States, the euro area, and China affect the currency composition of central banks' foreign exchange reserve…