research
∙
06/20/2023
On Compositionality and Improved Training of NADO
NeurAlly-Decomposed Oracle (NADO) is a powerful approach for controllabl...
share
research
∙
05/30/2023
Unsupervised Melody-to-Lyric Generation
Automatic melody-to-lyric generation is a task in which song lyrics are ...
research
∙
05/12/2023
Unsupervised Melody-Guided Lyrics Generation
Automatic song writing is a topic of significant practical interest. How...
research
∙
11/04/2021
Finite-Time Consensus Learning for Decentralized Optimization with Nonlinear Gossiping
Distributed learning has become an integral tool for scaling up machine ...
research
∙
11/04/2021
Variational Inference with Holder Bounds
The recent introduction of thermodynamic integration techniques has prov...
research
∙
07/05/2021
Imputation-Free Learning from Incomplete Observations
Although recent works have developed methods that can generate estimatio...
research
∙
12/06/2020
Proactive Pseudo-Intervention: Causally Informed Contrastive Learning For Interpretable Vision Models
Deep neural networks have shown significant promise in comprehending com...
research
∙
11/25/2020
Supercharging Imbalanced Data Learning With Causal Representation Transfer
Dealing with severe class imbalance poses a major challenge for real-wor...
research
∙
10/23/2020
Counterfactual Representation Learning with Balancing Weights
A key to causal inference with observational data is achieving balance i...
research
∙
10/15/2020
Double Robust Representation Learning for Counterfactual Prediction
Causal inference, or counterfactual prediction, is central to decision m...
research
∙
10/12/2020
Improving Text Generation with Student-Forcing Optimal Transport
Neural language models are often trained with maximum likelihood estimat...
research
∙
09/17/2020
Variational Disentanglement for Rare Event Modeling
Combining the increasing availability and abundance of healthcare data a...
research
∙
08/14/2020
Weakly supervised cross-domain alignment with optimal transport
Cross-domain alignment between image objects and text sequences is key t...
research
∙
04/30/2020
APo-VAE: Text Generation in Hyperbolic Space
Natural language often exhibits inherent hierarchical structure ingraine...
research
∙
03/09/2020
Variational Learning of Individual Survival Distributions
The abundance of modern health data provides many opportunities for the ...
research
∙
09/30/2019
Improving Textual Network Learning with Variational Homophilic Embeddings
The performance of many network learning applications crucially hinges o...
research
∙
06/05/2019
Improving Textual Network Embedding with Global Attention via Optimal Transport
Constituting highly informative network embeddings is an important tool ...
research
∙
05/21/2019
Survival Function Matching for Calibrated Time-to-Event Predictions
Models for predicting the time of a future event are crucial for risk as...
research
∙
01/18/2019
Improving Sequence-to-Sequence Learning via Optimal Transport
Sequence-to-sequence models are commonly trained via maximum likelihood ...
research
∙
09/17/2018
Adversarial Text Generation via Feature-Mover's Distance
Generative adversarial networks (GANs) have achieved significant success...
research
∙
04/09/2018
