Search Results for author:
Found 13 papers, 7 papers with code
SIXO: Smoothing Inference with Twisted Objectives
Sequential Monte Carlo (SMC) is an inference algorithm for state space models that approximates the posterior by sampling from a sequence of target distributions.
The Neural Testbed: Evaluating Joint Predictions
Predictive distributions quantify uncertainties ignored by point estimates.
Evaluating Predictive Distributions: Does Bayesian Deep Learning Work?
This paper introduces \textit{The Neural Testbed}, which provides tools for the systematic evaluation of agents that generate such predictions.
Energy-Inspired Models: Learning with Sampler-Induced Distributions
Motivated by this, we consider the sampler-induced distribution as the model of interest and maximize the likelihood of this model.
Revisiting Auxiliary Latent Variables in Generative Models
The success of enriching the variational family with auxiliary latent variables motivates applying the same techniques to the generative model.
Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives
Burda et al. (2015) introduced a multi-sample variational bound, IWAE, that is at least as tight as the standard variational lower bound and becomes increasingly tight as the number of samples increases.
An online sequence-to-sequence model for noisy speech recognition
This is because the models require that the entirety of the input sequence be available at the beginning of inference, an assumption that is not valid for instantaneous speech recognition.
Filtering Variational Objectives
When used as a surrogate objective for maximum likelihood estimation in latent variable models, the evidence lower bound (ELBO) produces state-of-the-art results.
Learning Hard Alignments with Variational Inference
There has recently been significant interest in hard attention models for tasks such as object recognition, visual captioning and speech recognition.
REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models
Learning in models with discrete latent variables is challenging due to high variance gradient estimators.
Particle Value Functions
The policy gradients of the expected return objective can react slowly to rare rewards.
Changing Model Behavior at Test-Time Using Reinforcement Learning
Machine learning models are often used at test-time subject to constraints and trade-offs not present at training-time.
Training a Subsampling Mechanism in Expectation
We describe a mechanism for subsampling sequences and show how to compute its expected output so that it can be trained with standard backpropagation.
