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

8 results for “SWAG”

The SWAG Algorithm; a Mathematical Approach that Outperforms Traditional Deep Learning. Theory and Implementationstat.ML

SWAG outperforms traditional neural networks on complex tasks.

problem Improving neural network performance on complex, non-linear tasks.

method SWAG uses a polynomial basis of activation functions in each layer.

result SWAG outperforms state-of-the-art neural networks in convergence and performance.

neural networks activation functions deep learning polynomial basis non-linear tasks

2018-11-28abs ↗pdf ↗

A Simple Baseline for Bayesian Uncertainty in Deep Learningcs.LG

SWAG improves deep learning uncertainty with a simple, scalable method.

problem Improving uncertainty estimation in deep learning models.

method SWAG uses stochastic weight averaging to fit a Gaussian distribution over neural network weights.

result SWAG approximates the true posterior and performs well on various tasks.

Bayesian uncertainty Deep learning Stochastic Weight Averaging Gaussian approximation Uncertainty calibration

2019-02-07abs ↗pdf ↗

SWAG: Item Recommendations using Convolutions on Weighted Graphscs.IR

SWAG uses graph convolutions to recommend products.

problem Product recommendation using graph-structured data.

method Graph Convolutional Network (GCN) with weighted random walks and aggregations.

result Graph-based approach improves product recommendations.

recommender systems graph neural networks product recommendations weighted graphs graph convolutions

2019-11-22abs ↗pdf ↗

Bayesian Pseudo Posterior Mechanism for Differentially Private Machine Learningstat.ML

New DP mechanism SWAG-PPM improves privacy in deep learning models.

problem Differential privacy struggles with real-world distributions, especially imbalanced data.

method SWAG-PPM uses a pseudo posterior distribution to downweight high-risk records.

result SWAG-PPM outperforms DP-SGD with similar privacy budget and modest utility degradation.

differential privacy deep learning imbalanced data text classification workplace injuries

2025-03-27abs ↗pdf ↗

How Reasonable are Common-Sense Reasoning Tasks: A Case-Study on the Winograd Schema Challenge and SWAGcs.LG

Study evaluates progress in common-sense reasoning tasks.

problem Assessing genuine progress in common-sense reasoning systems.

method Case studies of WSC and SWAG, protocol design to clarify results.

result Previous experimental designs had flaws, need for new protocols.

common-sense reasoning Winograd Schema Challenge SWAG experimental design genuine progress

2018-11-05abs ↗pdf ↗

SWAG: A Wrapper Method for Sparse Learningstat.ML

SWAG combines screening and wrapper methods for interpretable sparse learning.

problem Need for interpretable and replicable machine learning results in sparse settings.

method Greedy exploration of attribute space to find sparse learners.

result Library of equivalent learners for attribute availability.

sparse learning interpretability replicability wrapper method screening

2020-06-23abs ↗pdf ↗

Bayesian Generative Adversarial Networks via Gaussian Approximation for Tabular Data Synthesiscs.LG

GACTGAN synthesizes tabular data better with less computational overhead.

problem Synthesizing mixed tabular data while balancing risk and utility.

method Integrates Bayesian posterior approximation with Stochastic Weight Averaging-Gaussian (SWAG) in CTGAN.

result GACTGAN produces better synthetic data with reduced privacy risk.

Bayesian GAN CTGAN tabular data synthesis Gaussian approximation

2026-02-25abs ↗pdf ↗

UQ-ARMED: Uncertainty quantification of adversarially-regularized mixed effects deep learning for clustered non-iid datastat.ML

This research improves model interpretability and uncertainty estimation for deep learning models on non-iid data.

problem Improving interpretability and uncertainty estimation for deep learning models on non-iid data.

method 4 UQ approaches (BNN, SWAG, MC dropout, ensemble) applied to ARMED MEDL models.

result Ensemble approaches, especially with 90% subsampling, provide best performance in prediction and uncertainty estimation.

deep learning uncertainty quantification ensemble methods mixed effects models non-iid data

2022-11-29abs ↗pdf ↗