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.
Active-memory mechanisms can replace self-attention in Transformers, but optimal results often require both.
Recurrent neural networks (RNNs) provide state-of-the-art performance in processing sequential data but are memory intensive to train, limiting the flexibility of RNN models which can be trained. Reversible RNNs---RNNs for which the hidden-to-hidden transition can be reversed---offer a path to reduce the memory require…
A new memory replay mechanism improves reinforcement learning stability and speed.
Online Normalization is a new technique for normalizing the hidden activations of a neural network. Like Batch Normalization, it normalizes the sample dimension. While Online Normalization does not use batches, it is as accurate as Batch Normalization. We resolve a theoretical limitation of Batch Normalization by intro…
LASER compresses recursive model activations by exploiting their low-dimensional structure.
Serenity optimizes neural network execution for edge devices by scheduling with optimal memory footprint.
Improved deep learning model deployment on tiny MCUs with mixed-precision quantization.