Does Knowledge Distillation Really Work? | 0 | 0.34 | 2021 |
Neural Tangents - Fast and Easy Infinite Neural Networks in Python. | 0 | 0.34 | 2020 |
Neural Tangents: Fast and Easy Infinite Neural Networks in Python. | 0 | 0.34 | 2020 |
Ceb Improves Model Robustness | 0 | 0.34 | 2020 |
On the Use of ArXiv as a Dataset | 0 | 0.34 | 2019 |
Information in Infinite Ensembles of Infinitely-Wide Neural Networks | 0 | 0.34 | 2019 |
Variational Predictive Information Bottleneck | 0 | 0.34 | 2019 |
On Variational Bounds of Mutual Information. | 3 | 0.37 | 2019 |
Dueling Decoders: Regularizing Variational Autoencoder Latent Spaces. | 0 | 0.34 | 2019 |
Watch Your Step - Learning Node Embeddings via Graph Attention. | 5 | 0.40 | 2018 |
TherML: Thermodynamics of Machine Learning. | 0 | 0.34 | 2018 |
Fixing a Broken ELBO. | 20 | 0.69 | 2018 |
Uncertainty in the Variational Information Bottleneck. | 9 | 0.50 | 2018 |
GILBO: One Metric to Measure Them All. | 0 | 0.34 | 2018 |
β-VAEs can retain label information even at high compression. | 0 | 0.34 | 2018 |
GILBO: One Metric to Measure Them All. | 1 | 0.35 | 2018 |
An Information-Theoretic Analysis of Deep Latent-Variable Models. | 1 | 0.40 | 2017 |
Motion Prediction Under Multimodality with Conditional Stochastic Networks. | 0 | 0.34 | 2017 |
Deep Variational Information Bottleneck. | 0 | 0.34 | 2017 |
Watch Your Step: Learning Graph Embeddings Through Attention. | 6 | 0.44 | 2017 |
Jeffrey's prior sampling of deep sigmoidal networks. | 0 | 0.34 | 2017 |
Improved generator objectives for GANs. | 1 | 0.37 | 2016 |
DeepMath - Deep Sequence Models for Premise Selection. | 0 | 0.34 | 2016 |
Deep Variational Information Bottleneck. | 20 | 0.58 | 2016 |
Text Segmentation based on Semantic Word Embeddings. | 4 | 0.42 | 2015 |
Clustering via Content-Augmented Stochastic Blockmodels | 0 | 0.34 | 2015 |