Research
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
0.3%0.5%0.8%0.1% · Feb 202119922001200920182026
5 results for “self-adversarial”
Self-Adversarially Learned Bayesian Samplingstat.ML

Self-adversarial learning improves Bayesian sampling efficiency and quality.

problem Highly correlated and inefficient samples from scalable Bayesian sampling methods.
method Proposes a self-adversarial learning framework to learn a conditional generator.
result Efficiently generated samples that progressively approach a target distribution.
Bayesian samplingself-adversarial learningMarkov kernelsample qualitysampling efficiency
2018-11-21abs ↗pdf ↗
adVAE: A self-adversarial variational autoencoder with Gaussian anomaly prior knowledge for anomaly detectioncs.LG

Proposes a self-adversarial variational autoencoder for anomaly detection.

problem Anomaly detection in deep generative models.
method Self-adversarial Variational Autoencoder with Gaussian anomaly prior.
result Significant improvements in anomaly detection performance compared to SOTA baselines.
anomaly detectionself-adversarialvariational autoencoderGaussian priordeep generative models
2019-03-03abs ↗pdf ↗
EBMs Trained with Maximum Likelihood are Generator Models Trained with a Self-adverserial Losscs.LG

EBMs trained with ML are shown to behave like GANs with a self-adversarial loss.

problem Training EBMs with ML is intractable due to intractable unnormalized distributions.
method Replaced MCMC with deterministic gradient descent ODE solutions to study density induced by dynamics.
result EBM training is effectively a self-adversarial procedure rather than ML estimation.
Energy-based modelsMaximum likelihoodGradient descentGANsSelf-adversarial loss
2021-02-23abs ↗pdf ↗
RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecs.LG

RotatE embeds knowledge graphs using rotations in complex space for better link prediction.

problem Predicting missing links in knowledge graphs.
method RotatE models relations as rotations in complex vector space, using self-adversarial negative sampling.
result RotatE models and infers various relation patterns, outperforming existing models.
knowledge graph embeddinglink predictioncomplex vector spacerotationsnegative sampling
2019-02-26abs ↗pdf ↗