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.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “meta-weight-net”

Meta-Weight-Net: Learning an Explicit Mapping For Sample Weightingcs.LG

Adaptive learning of sample weights for better model performance.

problem Overfitting to biased training data with corrupted labels or class imbalance.

method Adaptive learning of an explicit weighting function using a meta-weight-net.

result Improves model accuracy in class imbalance and noisy label cases.

deep learning sample weighting overfitting meta-weight-net class imbalance

2019-02-20abs ↗pdf ↗

EvoGrad: Efficient Gradient-Based Meta-Learning and Hyperparameter Optimizationcs.LG

EvoGrad improves efficiency in meta-learning and hyperparameter optimization.

problem Efficiently compute hypergradients for larger network architectures.

method Uses evolutionary techniques to estimate hypergradients without second-order derivatives or longer computational graphs.

result Significant improvements in efficiency, enabling scaling to bigger architectures.

meta-learning hyperparameter optimization gradient-based evolutionary techniques second-order derivatives

2021-06-19abs ↗pdf ↗