Search Results for author:
Found 23 papers, 9 papers with code
Robust Inverse Graphics via Probabilistic Inference
How do we infer a 3D scene from a single image in the presence of corruptions like rain, snow or fog?
Training Chain-of-Thought via Latent-Variable Inference
Large language models (LLMs) solve problems more accurately and interpretably when instructed to work out the answer step by step using a ``chain-of-thought'' (CoT) prompt.
Neural Amortized Inference for Nested Multi-agent Reasoning
Multi-agent interactions, such as communication, teaching, and bluffing, often rely on higher-order social inference, i. e., understanding how others infer oneself.
ProbNeRF: Uncertainty-Aware Inference of 3D Shapes from 2D Images
The problem of inferring object shape from a single 2D image is underconstrained.
Drawing out of Distribution with Neuro-Symbolic Generative Models
We then adopt a subset of the Omniglot challenge tasks, and evaluate its ability to generate new exemplars (both unconditionally and conditionally), and perform one-shot classification, showing that DooD matches the state of the art.
Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interface
We build on a recent approach, Memoised Wake-Sleep (MWS), which alleviates part of the problem by memoising discrete variables, and extend it to allow for a principled and effective way to handle continuous variables by learning a separate recognition model used for importance-sampling based approximate inference and marginalization.
Learning Evolved Combinatorial Symbols with a Neuro-symbolic Generative Model
Humans have the ability to rapidly understand rich combinatorial concepts from limited data.
Learning to learn generative programs with Memoised Wake-Sleep
We study a class of neuro-symbolic generative models in which neural networks are used both for inference and as priors over symbolic, data-generating programs.
Semi-supervised Sequential Generative Models
We introduce a novel objective for training deep generative time-series models with discrete latent variables for which supervision is only sparsely available.
Amortized Population Gibbs Samplers with Neural Sufficient Statistics
We develop amortized population Gibbs (APG) samplers, a class of scalable methods that frames structured variational inference as adaptive importance sampling.
The Thermodynamic Variational Objective
We introduce the thermodynamic variational objective (TVO) for learning in both continuous and discrete deep generative models.
Revisiting Reweighted Wake-Sleep
Discrete latent-variable models, while applicable in a variety of settings, can often be difficult to learn.
Imitation Learning of Factored Multi-agent Reactive Models
We apply recent advances in deep generative modeling to the task of imitation learning from biological agents.
Deep Variational Reinforcement Learning for POMDPs
Many real-world sequential decision making problems are partially observable by nature, and the environment model is typically unknown.
Revisiting Reweighted Wake-Sleep for Models with Stochastic Control Flow
Stochastic control-flow models (SCFMs) are a class of generative models that involve branching on choices from discrete random variables.
Tighter Variational Bounds are Not Necessarily Better
We provide theoretical and empirical evidence that using tighter evidence lower bounds (ELBOs) can be detrimental to the process of learning an inference network by reducing the signal-to-noise ratio of the gradient estimator.
Improvements to Inference Compilation for Probabilistic Programming in Large-Scale Scientific Simulators
We consider the problem of Bayesian inference in the family of probabilistic models implicitly defined by stochastic generative models of data.
Bayesian Optimization for Probabilistic Programs
We present the first general purpose framework for marginal maximum a posteriori estimation of probabilistic program variables.
Auto-Encoding Sequential Monte Carlo
We build on auto-encoding sequential Monte Carlo (AESMC): a method for model and proposal learning based on maximizing the lower bound to the log marginal likelihood in a broad family of structured probabilistic models.
Using Synthetic Data to Train Neural Networks is Model-Based Reasoning
We draw a formal connection between using synthetic training data to optimize neural network parameters and approximate, Bayesian, model-based reasoning.
Sentiment Analysis for Low Resource Languages: A Study on Informal Indonesian Tweets
This paper describes our attempt to build a sentiment analysis system for Indonesian tweets.
Inference Compilation and Universal Probabilistic Programming
We introduce a method for using deep neural networks to amortize the cost of inference in models from the family induced by universal probabilistic programming languages, establishing a framework that combines the strengths of probabilistic programming and deep learning methods.
Data-driven Sequential Monte Carlo in Probabilistic Programming
Most of Markov Chain Monte Carlo (MCMC) and sequential Monte Carlo (SMC) algorithms in existing probabilistic programming systems suboptimally use only model priors as proposal distributions.
