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

5 results for “debuggability”

Leveraging Sparse Linear Layers for Debuggable Deep Networkscs.LG

Sparse linear models improve neural network debuggability.

problem Improving neural network interpretability and debugging.

method Using sparse linear models over learned deep feature representations.

result The approach leads to more debuggable and accurate neural networks.

neural networks interpretability debugging sparse models deep learning

2021-05-11abs ↗pdf ↗

Provable Training Set Debugging for Linear Regressioncs.LG

The paper develops methods to identify and correct buggy data in linear regression models.

problem Identifying and correcting buggy data in linear regression models.

method Formulated a general statistical algorithm for identifying buggy points, provided theoretical guarantees, and proposed an algorithm for tuning parameter selection.

result Theoretical guarantees and empirical results show the effectiveness of the proposed debugging algorithm.

linear regression buggy data M-estimation Lasso debugging

2020-06-16abs ↗pdf ↗

Synthesize, Execute and Debug: Learning to Repair for Neural Program Synthesiscs.LG

SED integrates synthesis, execution, and debugging for neural program synthesis.

problem Challenges in synthesizing complex programs that match specifications.

method SED combines synthesis, execution, and debugging to improve neural program generation.

result SED reduces error rates and outperforms standard decoding methods.

neural program synthesis program debugging deep learning Karel benchmark

2020-07-16abs ↗pdf ↗

An Introduction to Deep Visual Explanationstat.ML

Framework for understanding deep learning models through visual explanations.

problem Challenges of explainability and debuggability in deep learning.

method Develops a preliminary framework called 'deep visual explanation' (DVE) for understanding deep neural network models.

result Initial results show potential for interpretability in image classification.

deep learning explainability debuggability visual explanation image classification

2017-11-26abs ↗pdf ↗

Cockpit: A Practical Debugging Tool for the Training of Deep Neural Networkscs.LG

Cockpit provides tools for debugging deep neural networks during training.

problem Limited real-time training diagnostics for deep learning models.

method Cockpit uses novel higher-order information about gradient distribution and curvature.

result Facilitates identification of learning phases and failure modes.

deep learning debugging interpretability PyTorch gradient analysis

2021-02-12abs ↗pdf ↗