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.

169,341 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “Post-Learning”

Icing on the Cake: An Easy and Quick Post-Learnig Method You Can Try After Deep Learningcs.LG

A simple post-learning method boosts deep learning performance.

problem Improving classification performance in deep learning.

method Re-training the final classifier after initial training.

result Enhanced classification performance in deep learning.

Deep Learning Classification Post-Learning Performance Improvement

2018-07-17abs ↗pdf ↗

Model Aggregation via Good-Enough Model Spacescs.LG

GEMS learns global models by intersecting local 'good-enough' models.

problem Aggregating data across multiple nodes with limited communication.

method GEMS framework that intersects 'good-enough' models from each node.

result GEMS improves model accuracy by 15 points on average.

model aggregation distributed learning machine learning good-enough models minimal communication

2018-05-20abs ↗pdf ↗

Thermodynamic limit in learning period threestat.ML

Learning three data points can generate all types of periodic orbits in a neural network.

problem Can learning three data points generate all types of periodic orbits in a neural network?

method Investigated a continuous one-dimensional map with period three in a random neural network in its thermodynamic limit.

result Almost all learned periods are unstable, and each network has its own characteristic attractors.

period three neural network thermodynamic limit universality attractors

2024-05-12abs ↗pdf ↗

Controlling Continuous Relaxation for Combinatorial Optimizationstat.ML

CRA improves UL-based CO solvers by dynamically smoothing and enforcing discreteness.

problem Local optima and artificial rounding issues in UL-based CO solvers.

method Continuous Relaxation Annealing (CRA) strategy that dynamically shifts from continuous to discrete solutions.

result Significantly enhances UL-based CO solver performance and eliminates artificial rounding.

Continuous Relaxation Combinatorial Optimization Unsupervised Learning Local Optima Artificial Rounding

2023-09-29abs ↗pdf ↗