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 “Maddness”

A scalable version of MADD for big-data classificationstat.ME

A scalable version of MADD improves big-data classification speed.

problem High computational complexity of MADD in big data.

method Selecting a representative set and using Random Fourier Features.

result Achieves similar performance to MADD but at a fraction of the computing time.

MADD big data scalability Random Fourier Features Euclidean distance

2026-07-09abs ↗pdf ↗

Stella Nera: A Differentiable Maddness-Based Hardware Accelerator for Efficient Approximate Matrix Multiplicationcs.AR

Stella Nera accelerates matrix multiplications with a hash-based approach, achieving high energy efficiency and accuracy.

problem High computational and energy demands due to matrix multiplications in AI models.

method Stella Nera uses Maddness, a hash-based product quantization, to eliminate multipliers and achieve lookups and additions.

result Achieved an energy efficiency of 161 TOp/s/W@0.55V, 25x better than conventional MatMul accelerators.

Maddness Matrix Multiplication Differentiable Energy Efficiency Gradient-Based

2023-11-16abs ↗pdf ↗

A Fair Post-Processing Method based on the MADD Metric for Predictive Student Modelscs.CY

Develops a fair post-processing method for student success predictions.

problem Ensuring fairness in predictive student models for educational applications.

method Uses the MADD metric to improve model fairness while maintaining accuracy.

result Successfully improved fairness of predictive models for student success.

Predictive models Student success Algorithmic fairness MADD metric Post-processing

2024-07-07abs ↗pdf ↗

Is Your Model "MADD"? A Novel Metric to Evaluate Algorithmic Fairness for Predictive Student Modelscs.LG

New metric MADD assesses fairness of predictive student models.

problem Predictive student models can be biased and unfair, leading to discrimination.

method Proposes MADD metric to analyze model's discriminatory behaviors.

result Fair predictive performance does not guarantee fair behaviors or outcomes.

algorithmic fairness predictive models student success data bias model behavior

2023-05-24abs ↗pdf ↗