A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
IA-BMA adapts model weights to inputs for better predictions.
DFS dynamically decides bitwidths for layers to balance accuracy and efficiency.
While variational dropout approaches have been shown to be effective for network sparsification, they are still suboptimal in the sense that they set the dropout rate for each neuron without consideration of the input data. With such input-independent dropout, each neuron is evolved to be generic across inputs, which m…
Optimal model averaging for conditional generative models improves performance across various data types.
Meta-learned confidence improves few-shot learning accuracy.