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.
Study identifies three quantization regimes for ReLU networks.
PyKEEN 1.0 simplifies KGE model creation and optimization.
We propose two optimization techniques to minimize memory usage and computation while meeting system timing constraints for real-time classification in wearable systems. Our method derives a hierarchical classifier structure for Support Vector Machine (SVM) in order to reduce the amount of computations, based on the pr…
OpTorch optimizes deep learning for resource-limited environments.
POET enables large neural network training on tiny devices with reduced energy.
A new memory-efficient Adam variant reduces second moments when feasible.
HybridSGD improves SGD performance by balancing computation and communication.
Large deep learning models offer significant accuracy gains, but training billions to trillions of parameters is challenging. Existing solutions such as data and model parallelisms exhibit fundamental limitations to fit these models into limited device memory, while obtaining computation, communication and development …
Chronicals boosts LLM fine-tuning speed by 3.51x over Unsloth.