research
∙
07/31/2023
Don't be so negative! Score-based Generative Modeling with Oracle-assisted Guidance
The maximum likelihood principle advocates parameter estimation via opti...
share
research
∙
05/24/2023
Realistically distributing object placements in synthetic training data improves the performance of vision-based object detection models
When training object detection models on synthetic data, it is important...
research
∙
05/19/2023
Video Killed the HD-Map: Predicting Driving Behavior Directly From Drone Images
The development of algorithms that learn behavioral driving models using...
research
∙
03/28/2023
Visual Chain-of-Thought Diffusion Models
Recent progress with conditional image diffusion models has been stunnin...
research
∙
10/21/2022
Uncertain Evidence in Probabilistic Models and Stochastic Simulators
We consider the problem of performing Bayesian inference in probabilisti...
research
∙
10/20/2022
Graphically Structured Diffusion Models
We introduce a framework for automatically defining and learning deep ge...
research
∙
08/09/2022
Vehicle Type Specific Waypoint Generation
We develop a generic mechanism for generating vehicle-type specific sequ...
research
∙
06/17/2022
Conditional Permutation Invariant Flows
We present a novel, conditional generative probabilistic model of set-va...
research
∙
05/30/2022
Critic Sequential Monte Carlo
We introduce CriticSMC, a new algorithm for planning as inference built ...
research
∙
05/23/2022
Flexible Diffusion Modeling of Long Videos
We present a framework for video modeling based on denoising diffusion p...
research
∙
05/20/2022
BayesPCN: A Continually Learnable Predictive Coding Associative Memory
Associative memory plays an important role in human intelligence and its...
research
∙
02/17/2022
Gradients without Backpropagation
Using backpropagation to compute gradients of objective functions for op...
research
∙
02/06/2022
Exploration with Multi-Sample Target Values for Distributional Reinforcement Learning
Distributional reinforcement learning (RL) aims to learn a value-network...
research
∙
01/13/2022
Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning
Modern deep learning requires large-scale extensively labelled datasets ...
research
∙
07/01/2021
q-Paths: Generalizing the Geometric Annealing Path using Power Means
Many common machine learning methods involve the geometric annealing pat...
research
∙
06/18/2021
Differentiable Particle Filtering without Modifying the Forward Pass
In recent years particle filters have being used as components in system...
research
∙
04/22/2021
Imagining The Road Ahead: Multi-Agent Trajectory Prediction via Differentiable Simulation
We develop a deep generative model built on a fully differentiable simul...
research
∙
02/24/2021
Image Completion via Inference in Deep Generative Models
We consider image completion from the perspective of amortized inference...
research
∙
12/31/2020
Robust Asymmetric Learning in POMDPs
Policies for partially observed Markov decision processes can be efficie...
research
∙
12/14/2020
Annealed Importance Sampling with q-Paths
Annealed importance sampling (AIS) is the gold standard for estimating p...
research
∙
12/10/2020
Ensemble Squared: A Meta AutoML System
The continuing rise in the number of problems amenable to machine learni...
research
∙
10/29/2020
Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective
Achieving the full promise of the Thermodynamic Variational Objective (T...
research
∙
10/08/2020
Uncertainty in Neural Processes
We explore the effects of architecture and training objective choice on ...
research
∙
10/03/2020
Assisting the Adversary to Improve GAN Training
We propose a method for improved training of generative adversarial netw...
research
∙
07/01/2020
All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference
The recently proposed Thermodynamic Variational Objective (TVO) leverage...
research
∙
06/30/2020
Semi-supervised Sequential Generative Models
We introduce a novel objective for training deep generative time-series ...
research
∙
06/17/2020
Improving Few-Shot Visual Classification with Unlabelled Examples
We propose a transductive meta-learning method that uses unlabelled inst...
research
∙
03/30/2020
Planning as Inference in Epidemiological Models
In this work we demonstrate how existing software tools can be used to a...
research
∙
03/28/2020
Coping With Simulators That Don't Always Return
Deterministic models are approximations of reality that are easy to inte...
research
∙
12/07/2019
Improved Few-Shot Visual Classification
Few-shot learning is a fundamental task in computer vision that carries ...
research
∙
10/25/2019
Attention for Inference Compilation
We present a new approach to automatic amortized inference in universal ...
research
∙
10/25/2019
Deep Probabilistic Surrogate Networks for Universal Simulator Approximation
We present a framework for automatically structuring and training fast, ...
research
∙
10/20/2019
Amortized Rejection Sampling in Universal Probabilistic Programming
Existing approaches to amortized inference in probabilistic programs wit...
research
∙
09/20/2019
Safer End-to-End Autonomous Driving via Conditional Imitation Learning and Command Augmentation
Imitation learning is a promising approach to end-to-end training of aut...
research
∙
07/24/2019
The Virtual Patch Clamp: Imputing C. elegans Membrane Potentials from Calcium Imaging
We develop a stochastic whole-brain and body simulator of the nematode r...
research
∙
07/18/2019
Amortized Monte Carlo Integration
Current approaches to amortizing Bayesian inference focus solely on appr...
research
∙
07/08/2019
Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale
Probabilistic programming languages (PPLs) are receiving widespread atte...
research
∙
06/28/2019
The Thermodynamic Variational Objective
We introduce the thermodynamic variational objective (TVO) for learning ...
research
∙
06/13/2019
Near-Optimal Glimpse Sequences for Improved Hard Attention Neural Network Training
We introduce the use of Bayesian optimal experimental design techniques ...
research
∙
03/12/2019
Imitation Learning of Factored Multi-agent Reactive Models
We apply recent advances in deep generative modeling to the task of imit...
research
∙
03/06/2019
LF-PPL: A Low-Level First Order Probabilistic Programming Language for Non-Differentiable Models
We develop a new Low-level, First-order Probabilistic Programming Langua...
research
∙
09/27/2018
An Introduction to Probabilistic Programming
This document is designed to be a first-year graduate-level introduction...
research
∙
07/20/2018
Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model
We present a novel framework that enables efficient probabilistic infere...
research
∙
06/25/2018
Inference Trees: Adaptive Inference with Exploration
We introduce inference trees (ITs), a new class of inference methods tha...
research
∙
06/06/2018
Deep Variational Reinforcement Learning for POMDPs
Many real-world sequential decision making problems are partially observ...
research
∙
05/26/2018
Revisiting Reweighted Wake-Sleep
Discrete latent-variable models, while applicable in a variety of settin...
research
∙
04/07/2018
Discontinuous Hamiltonian Monte Carlo for Probabilistic Programs
Hamiltonian Monte Carlo (HMC) is the dominant statistical inference algo...
research
∙
03/12/2018
High Throughput Synchronous Distributed Stochastic Gradient Descent
We introduce a new, high-throughput, synchronous, distributed, data-para...
research
∙
02/13/2018
Tighter Variational Bounds are Not Necessarily Better
We provide theoretical and empirical evidence that using tighter evidenc...
research
∙
12/21/2017