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.
Improved pruning method using iterative sensitivity ranking before training.
Improved pruning method finds winning neural network subnetworks.
Simple iterative method reduces deep network size significantly.
We propose a practical approach based on federated learning to solve out-of-domain issues with continuously running embedded speech-based models such as wake word detectors. We conduct an extensive empirical study of the federated averaging algorithm for the "Hey Snips" wake word based on a crowdsourced dataset that mi…
We explore the application of end-to-end stateless temporal modeling to small-footprint keyword spotting as opposed to recurrent networks that model long-term temporal dependencies using internal states. We propose a model inspired by the recent success of dilated convolutions in sequence modeling applications, allowin…
Recent pruning methods at initialization fall short of random pruning's accuracy.
Unified model for sequence labeling and classification.
Researchers analyze how RNNs solve intent detection tasks using dynamical systems theory.
New framework for evaluating ad auctions using stochastic modeling.