Search Results for author:
Found 8 papers, 3 papers with code
Credibility-Aware Multi-Modal Fusion Using Probabilistic Circuits
We consider the problem of late multi-modal fusion for discriminative learning.
Building Expressive and Tractable Probabilistic Generative Models: A Review
We present a comprehensive survey of the advancements and techniques in the field of tractable probabilistic generative modeling, primarily focusing on Probabilistic Circuits (PCs).
VQ-Flows: Vector Quantized Local Normalizing Flows
Normalizing flows provide an elegant approach to generative modeling that allows for efficient sampling and exact density evaluation of unknown data distributions.
Task Attended Meta-Learning for Few-Shot Learning
The popular approaches for ML either learn a generalizable initial model or a generic parametric optimizer through episodic training.
On Characterizing GAN Convergence Through Proximal Duality Gap
Finally, we validate experimentally the usefulness of proximal duality gap for monitoring and influencing GAN training.
Stress Testing of Meta-learning Approaches for Few-shot Learning
Our results show a quick degradation in the performance of initialization strategies for ML (MAML, TAML, and MetaSGD), while surprisingly, approaches that use an optimization strategy (MetaLSTM) perform significantly better.
Learning Neural Networks on SVD Boosted Latent Spaces for Semantic Classification
The availability of large amounts of data and compelling computation power have made deep learning models much popular for text classification and sentiment analysis.
On Duality Gap as a Measure for Monitoring GAN Training
Further, we show that our estimate, with its ability to identify model convergence/divergence, is a potential performance measure that can be used to tune the hyperparameters of a GAN.
