Search Results for author:
Found 16 papers, 10 papers with code
Denoising Diffusion Samplers
Denoising Diffusion Samplers (DDS) are obtained by approximating the corresponding time-reversal.
Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC
In this work, we build upon these ideas using the score-based interpretation of diffusion models, and explore alternative ways to condition, modify, and reuse diffusion models for tasks involving compositional generation and guidance.
Continuous diffusion for categorical data
Diffusion models have quickly become the go-to paradigm for generative modelling of perceptual signals (such as images and sound) through iterative refinement.
Self-conditioned Embedding Diffusion for Text Generation
Can continuous diffusion models bring the same performance breakthrough on natural language they did for image generation?
Learning to Navigate Wikipedia by Taking Random Walks
A fundamental ability of an intelligent web-based agent is seeking out and acquiring new information.
Score-Based Diffusion meets Annealed Importance Sampling
To obtain an importance sampling estimate of the marginal likelihood, AIS introduces an extended target distribution to reweight the Markov chain proposal.
Directly Training Joint Energy-Based Models for Conditional Synthesis and Calibrated Prediction of Multi-Attribute Data
We find our models are capable of both accurate, calibrated predictions and high-quality conditional synthesis of novel attribute combinations.
Oops I Took A Gradient: Scalable Sampling for Discrete Distributions
We propose a general and scalable approximate sampling strategy for probabilistic models with discrete variables.
No MCMC for me: Amortized sampling for fast and stable training of energy-based models
Energy-Based Models (EBMs) present a flexible and appealing way to represent uncertainty.
Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling
We estimate the Stein discrepancy between the data density $p(x)$ and the model density $q(x)$ defined by a vector function of the data.
Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One
In this setting, the standard class probabilities can be easily computed as well as unnormalized values of p(x) and p(x|y).
Understanding the Limitations of Conditional Generative Models
Class-conditional generative models hold promise to overcome the shortcomings of their discriminative counterparts.
Invertible Residual Networks
We show that standard ResNet architectures can be made invertible, allowing the same model to be used for classification, density estimation, and generation.
Ranked #5 on
Image Generation
on MNIST
FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
The result is a continuous-time invertible generative model with unbiased density estimation and one-pass sampling, while allowing unrestricted neural network architectures.
Ranked #1 on
Density Estimation
on UCI MINIBOONE
Backpropagation through the Void: Optimizing control variates for black-box gradient estimation
Gradient-based optimization is the foundation of deep learning and reinforcement learning.
Disentangling Space and Time in Video with Hierarchical Variational Auto-encoders
In this paper we propose a probabilistic approach for learning separable representations of object identity and pose information using unsupervised video data.
