Search Results for author:
Found 15 papers, 5 papers with code
Concrete Score Matching: Generalized Score Matching for Discrete Data
To this end, we propose an analogous score function called the "Concrete score", a generalization of the (Stein) score for discrete settings.
LMPriors: Pre-Trained Language Models as Task-Specific Priors
Particularly in low-data regimes, an outstanding challenge in machine learning is developing principled techniques for augmenting our models with suitable priors.
ButterflyFlow: Building Invertible Layers with Butterfly Matrices
Normalizing flows model complex probability distributions using maps obtained by composing invertible layers.
Counterbalancing Teacher: Regularizing Batch Normalized Models for Robustness
Batch normalization (BN) is a ubiquitous technique for training deep neural networks that accelerates their convergence to reach higher accuracy.
Density Ratio Estimation via Infinitesimal Classification
We then estimate the instantaneous rate of change of the bridge distributions indexed by time (the "time score") -- a quantity defined analogously to data (Stein) scores -- with a novel time score matching objective.
Featurized Density Ratio Estimation
Density ratio estimation serves as an important technique in the unsupervised machine learning toolbox.
Robust Representation Learning via Perceptual Similarity Metrics
A fundamental challenge in artificial intelligence is learning useful representations of data that yield good performance on a downstream task, without overfitting to spurious input features.
Neural Network Compression for Noisy Storage Devices
Compression and efficient storage of neural network (NN) parameters is critical for applications that run on resource-constrained devices.
Learning Task-Relevant Features via Contrastive Input Morphing
A fundamental challenge in artificial intelligence is learning useful representations of data that yield good performance on a downstream classification task, without overfitting to spurious input features.
Noisy Neural Network Compression for Analog Storage Devices
Efficient compression and storage of neural network (NN) parameters is critical for resource-constrained, downstream machine learning applications.
Encoding Musical Style with Transformer Autoencoders
We consider the problem of learning high-level controls over the global structure of generated sequences, particularly in the context of symbolic music generation with complex language models.
Fair Generative Modeling via Weak Supervision
Real-world datasets are often biased with respect to key demographic factors such as race and gender.
Meta-Amortized Variational Inference and Learning
Despite the recent success in probabilistic modeling and their applications, generative models trained using traditional inference techniques struggle to adapt to new distributions, even when the target distribution may be closely related to the ones seen during training.
Neural Joint Source-Channel Coding
For reliable transmission across a noisy communication channel, classical results from information theory show that it is asymptotically optimal to separate out the source and channel coding processes.
NECST: Neural Joint Source-Channel Coding
For reliable transmission across a noisy communication channel, classical results from information theory show that it is asymptotically optimal to separate out the source and channel coding processes.
