On-device research index

arXiv research

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.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “Graphcore IPU”

Making EfficientNet More Efficient: Exploring Batch-Independent Normalization, Group Convolutions and Reduced Resolution Trainingcs.LG

Researchers enhance EfficientNet models for practical efficiency on Graphcore IPU.

problem Improving practical efficiency of EfficientNet models on high-performance accelerators.

method Group convolutions, proxy-normalized activations, and reduced training resolution.

result Improves practical efficiency for both training and inference on Graphcore IPU.

EfficientNet Graphcore IPU Group Convolutions Proxy-Normalized Activations Reduced Resolution Training

2021-06-07abs ↗pdf ↗

Multi-Horizon Forecasting for Limit Order Books: Novel Deep Learning Approaches and Hardware Acceleration using Intelligent Processing Unitscs.LG

Deep learning models forecast stock market orders over multiple time frames.

problem Forecasting stock market orders over varying time frames.

method Encoder-decoder models with sequence-to-sequence and Attention mechanisms, leveraging Intelligent Processing Units (IPUs) for faster training.

result Multi-horizon forecasting outperforms single-horizon models, especially for long prediction periods.

deep learning forecasting limit order book sequence-to-sequence attention

2021-05-21abs ↗pdf ↗

Position Masking for Language Modelscs.CL

Expands MLM by masking token positions, improving performance and convergence.

problem Improving language model performance and convergence.

method Masking token positions along with [MASK] tokens, using a fully connected classifier stage.

result Shows .3% improvement and 50% faster convergence for BERT Base with position masking.

language models masked language modeling token masking BERT performance improvement

2020-06-02abs ↗pdf ↗

Predicting Invoice Dilution in Supply Chain Finance with Leakage Free Two Stage XGBoost, KAN (Kolmogorov Arnold Networks), and Ensemble Modelscs.AI

AI framework predicts invoice dilution in supply chain finance.

problem Invoice dilution risk in supply chain finance.

method AI, machine learning, dynamic credit limits, real-time projections.

result Supplemental AI model improves prediction accuracy.

invoice dilution supply chain finance AI machine learning dynamic credit limits

2026-02-16abs ↗pdf ↗