Search Results for author:
Found 98 papers, 41 papers with code
All in the (Exponential) Family: Information Geometry and Thermodynamic Variational Inference
While the Evidence Lower Bound (ELBO) has become a ubiquitous objective for variational inference, the recently proposed Thermodynamic Variational Objective (TVO) leverages thermodynamic integration to provide a tighter and more general family of bounds.
All-in-one simulation-based inference
Amortized Bayesian inference trains neural networks to solve stochastic inference problems using model simulations, thereby making it possible to rapidly perform Bayesian inference for any newly observed data.
On the Challenges and Opportunities in Generative AI
The field of deep generative modeling has grown rapidly and consistently over the years.
Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learning
Our solution, Layerwise Proximal Replay (LPR), balances learning from new and replay data while only allowing for gradual changes in the hidden activation of past data.
Nearest Neighbour Score Estimators for Diffusion Generative Models
Score function estimation is the cornerstone of both training and sampling from diffusion generative models.
Don't be so negative! Score-based Generative Modeling with Oracle-assisted Guidance
The maximum likelihood principle advocates parameter estimation via optimization of the data likelihood function.
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 to make the distribution of synthetic data as close as possible to the distribution of real data.
Video Killed the HD-Map: Predicting Multi-Agent Behavior Directly From Aerial Images
The development of algorithms that learn multi-agent behavioral models using human demonstrations has led to increasingly realistic simulations in the field of autonomous driving.
Visual Chain-of-Thought Diffusion Models
Recent progress with conditional image diffusion models has been stunning, and this holds true whether we are speaking about models conditioned on a text description, a scene layout, or a sketch.
Uncertain Evidence in Probabilistic Models and Stochastic Simulators
We consider the problem of performing Bayesian inference in probabilistic models where observations are accompanied by uncertainty, referred to as "uncertain evidence."
Graphically Structured Diffusion Models
We introduce a framework for automatically defining and learning deep generative models with problem-specific structure.
Vehicle Type Specific Waypoint Generation
We develop a generic mechanism for generating vehicle-type specific sequences of waypoints from a probabilistic foundation model of driving behavior.
Conditional Permutation Invariant Flows
We present a novel, conditional generative probabilistic model of set-valued data with a tractable log density.
Critic Sequential Monte Carlo
We introduce CriticSMC, a new algorithm for planning as inference built from a composition of sequential Monte Carlo with learned Soft-Q function heuristic factors.
Flexible Diffusion Modeling of Long Videos
We present a framework for video modeling based on denoising diffusion probabilistic models that produces long-duration video completions in a variety of realistic environments.
BayesPCN: A Continually Learnable Predictive Coding Associative Memory
Associative memory plays an important role in human intelligence and its mechanisms have been linked to attention in machine learning.
Gradients without Backpropagation
Using backpropagation to compute gradients of objective functions for optimization has remained a mainstay of machine learning.
Exploration with Multi-Sample Target Values for Distributional Reinforcement Learning
Distributional reinforcement learning (RL) aims to learn a value-network that predicts the full distribution of the returns for a given state, often modeled via a quantile-based critic.
Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning
The first method, Simple CNAPS, employs a hierarchically regularized Mahalanobis-distance based classifier combined with a state of the art neural adaptive feature extractor to achieve strong performance on Meta-Dataset, mini-ImageNet and tiered-ImageNet benchmarks.
q-Paths: Generalizing the Geometric Annealing Path using Power Means
Many common machine learning methods involve the geometric annealing path, a sequence of intermediate densities between two distributions of interest constructed using the geometric average.
Differentiable Particle Filtering without Modifying the Forward Pass
Particle filters are not compatible with automatic differentiation due to the presence of discrete resampling steps.
Imagining The Road Ahead: Multi-Agent Trajectory Prediction via Differentiable Simulation
We develop a deep generative model built on a fully differentiable simulator for multi-agent trajectory prediction.
Conditional Image Generation by Conditioning Variational Auto-Encoders
We present a conditional variational auto-encoder (VAE) which, to avoid the substantial cost of training from scratch, uses an architecture and training objective capable of leveraging a foundation model in the form of a pretrained unconditional VAE.
Near-Optimal Glimpse Sequences for Training Hard Attention Neural Networks
We introduce methodology from the BOED literature to approximate this optimal behaviour, and use it to generate `near-optimal' sequences of attention locations.
Robust Asymmetric Learning in POMDPs
Policies for partially observed Markov decision processes can be efficiently learned by imitating policies for the corresponding fully observed Markov decision processes.
Annealed Importance Sampling with q-Paths
Annealed importance sampling (AIS) is the gold standard for estimating partition functions or marginal likelihoods, corresponding to importance sampling over a path of distributions between a tractable base and an unnormalized target.
Ensemble Squared: A Meta AutoML System
There are currently many barriers that prevent non-experts from exploiting machine learning solutions ranging from the lack of intuition on statistical learning techniques to the trickiness of hyperparameter tuning.
Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective
Achieving the full promise of the Thermodynamic Variational Objective (TVO), a recently proposed variational lower bound on the log evidence involving a one-dimensional Riemann integral approximation, requires choosing a "schedule" of sorted discretization points.
Uncertainty in Neural Processes
We aim this work to be a counterpoint to a recent trend in the literature that stresses achieving good samples when the amount of conditioning data is large.
Assisting the Adversary to Improve GAN Training
Some of the most popular methods for improving the stability and performance of GANs involve constraining or regularizing the discriminator.
Improving Few-Shot Visual Classification with Unlabelled Examples
We propose a transductive meta-learning method that uses unlabelled instances to improve few-shot image classification performance.
All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference
We propose to choose intermediate distributions using equal spacing in the moment parameters of our exponential family, which matches grid search performance and allows the schedule to adaptively update over the course of training.
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.
Enhancing Few-Shot Image Classification with Unlabelled Examples
We develop a transductive meta-learning method that uses unlabelled instances to improve few-shot image classification performance.
Ranked #1 on
Few-Shot Image Classification
on Tiered ImageNet 10-way (1-shot)
(using extra training data)
Planning as Inference in Epidemiological Models
In this work we demonstrate how to automate parts of the infectious disease-control policy-making process via performing inference in existing epidemiological models.
Coping With Simulators That Don't Always Return
Deterministic models are approximations of reality that are easy to interpret and often easier to build than stochastic alternatives.
Improved Few-Shot Visual Classification
Few-shot learning is a fundamental task in computer vision that carries the promise of alleviating the need for exhaustively labeled data.
Ranked #2 on
Few-Shot Image Classification
on Mini-Imagenet 10-way (5-shot)
(using extra training data)
Attention for Inference Compilation
We present a new approach to automatic amortized inference in universal probabilistic programs which improves performance compared to current methods.
Probabilistic Surrogate Networks for Simulators with Unbounded Randomness
Our surrogates target stochastic simulators where the number of random variables itself can be stochastic and potentially unbounded.
Amortized Rejection Sampling in Universal Probabilistic Programming
Naive approaches to amortized inference in probabilistic programs with unbounded loops can produce estimators with infinite variance.
Efficient Bayesian Inference for Nested Simulators
We introduce two approaches for conducting efficient Bayesian inference in stochastic simulators containing nested stochastic sub-procedures, i. e., internal procedures for which the density cannot be calculated directly such as rejection sampling loops.
Efficient Inference Amortization in Graphical Models using Structured Continuous Conditional Normalizing Flows
We introduce a more efficient neural architecture for amortized inference, which combines continuous and conditional normalizing flows using a principled choice of structure.
Coping With Simulators That Don’t Always Return
Deterministic models are approximations of reality that are often easier to build and interpret than stochastic alternatives.
Safer End-to-End Autonomous Driving via Conditional Imitation Learning and Command Augmentation
On top of that, we extend our model with an additional latent variable and augment the dataset to train a controller that is robust to unsafe commands, such as asking it to turn into a wall.
The Virtual Patch Clamp: Imputing C. elegans Membrane Potentials from Calcium Imaging
We develop a stochastic whole-brain and body simulator of the nematode roundworm Caenorhabditis elegans (C. elegans) and show that it is sufficiently regularizing to allow imputation of latent membrane potentials from partial calcium fluorescence imaging observations.
Amortized Monte Carlo Integration
At runtime, samples are produced separately from each amortized proposal, before being combined to an overall estimate of the expectation.
Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale
Probabilistic programming languages (PPLs) are receiving widespread attention for performing Bayesian inference in complex generative models.
The Thermodynamic Variational Objective
We introduce the thermodynamic variational objective (TVO) for learning in both continuous and discrete deep generative models.
Near-Optimal Glimpse Sequences for Improved Hard Attention Neural Network Training
We introduce methodology from the BOED literature to approximate this optimal behaviour, and use it to generate `near-optimal' sequences of attention locations.
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.
LF-PPL: A Low-Level First Order Probabilistic Programming Language for Non-Differentiable Models
We develop a new Low-level, First-order Probabilistic Programming Language (LF-PPL) suited for models containing a mix of continuous, discrete, and/or piecewise-continuous variables.
Bayesian Distributed Stochastic Gradient Descent
We introduce Bayesian distributed stochastic gradient descent (BDSGD), a high-throughput algorithm for training deep neural networks on parallel clusters.
An Introduction to Probabilistic Programming
We start with a discussion of model-based reasoning and explain why conditioning is a foundational computation central to the fields of probabilistic machine learning and artificial intelligence.
Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model
We present a novel probabilistic programming framework that couples directly to existing large-scale simulators through a cross-platform probabilistic execution protocol, which allows general-purpose inference engines to record and control random number draws within simulators in a language-agnostic way.
Inference Trees: Adaptive Inference with Exploration
We introduce inference trees (ITs), a new class of inference methods that build on ideas from Monte Carlo tree search to perform adaptive sampling in a manner that balances exploration with exploitation, ensures consistency, and alleviates pathologies in existing adaptive methods.
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.
Hamiltonian Monte Carlo for Probabilistic Programs with Discontinuities
Hamiltonian Monte Carlo (HMC) is arguably the dominant statistical inference algorithm used in most popular "first-order differentiable" Probabilistic Programming Languages (PPLs).
High Throughput Synchronous Distributed Stochastic Gradient Descent
We introduce a new, high-throughput, synchronous, distributed, data-parallel, stochastic-gradient-descent learning algorithm.
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.
Towards a Testable Notion of Generalization for Generative Adversarial Networks
We consider the question of how to assess generative adversarial networks, in particular with respect to whether or not they generalise beyond memorising the training data.
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.
Faithful Inversion of Generative Models for Effective Amortized Inference
Inference amortization methods share information across multiple posterior-inference problems, allowing each to be carried out more efficiently.
Updating the VESICLE-CNN Synapse Detector
The original implementation makes use of a patch-based approach.
On Nesting Monte Carlo Estimators
Many problems in machine learning and statistics involve nested expectations and thus do not permit conventional Monte Carlo (MC) estimation.
Bayesian Optimization for Probabilistic Programs
We present the first general purpose framework for marginal maximum a posteriori estimation of probabilistic program variables.
Learning Disentangled Representations with Semi-Supervised Deep Generative Models
We propose to learn such representations using model architectures that generalise from standard VAEs, employing a general graphical model structure in the encoder and decoder.
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.
Online Learning Rate Adaptation with Hypergradient Descent
We introduce a general method for improving the convergence rate of gradient-based optimizers that is easy to implement and works well in practice.
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.
On the Pitfalls of Nested Monte Carlo
In this paper, we analyse the behaviour of nested Monte Carlo (NMC) schemes, for which classical convergence proofs are insufficient.
Inducing Interpretable Representations with Variational Autoencoders
We develop a framework for incorporating structured graphical models in the \emph{encoders} of variational autoencoders (VAEs) that allows us to induce interpretable representations through approximate variational inference.
Probabilistic structure discovery in time series data
Existing methods for structure discovery in time series data construct interpretable, compositional kernels for Gaussian process regression models.
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.
Spreadsheet Probabilistic Programming
We demonstrate this by developing a native Excel implementation of both a particle Markov Chain Monte Carlo variant and black-box variational inference for spreadsheet probabilistic programming.
Inference Networks for Sequential Monte Carlo in Graphical Models
We introduce a new approach for amortizing inference in directed graphical models by learning heuristic approximations to stochastic inverses, designed specifically for use as proposal distributions in sequential Monte Carlo methods.
Interacting Particle Markov Chain Monte Carlo
We introduce interacting particle Markov chain Monte Carlo (iPMCMC), a PMCMC method based on an interacting pool of standard and conditional sequential Monte Carlo samplers.
Semantics for probabilistic programming: higher-order functions, continuous distributions, and soft constraints
We study the semantic foundation of expressive probabilistic programming languages, that support higher-order functions, continuous distributions, and soft constraints (such as Anglican, Church, and Venture).
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.
Canonical Correlation Forests
We introduce canonical correlation forests (CCFs), a new decision tree ensemble method for classification and regression.
Black-Box Policy Search with Probabilistic Programs
In this work, we explore how probabilistic programs can be used to represent policies in sequential decision problems.
A New Approach to Probabilistic Programming Inference
We introduce and demonstrate a new approach to inference in expressive probabilistic programming languages based on particle Markov chain Monte Carlo.
Maximum a Posteriori Estimation by Search in Probabilistic Programs
We introduce an approximate search algorithm for fast maximum a posteriori probability estimation in probabilistic programs, which we call Bayesian ascent Monte Carlo (BaMC).
Path Finding under Uncertainty through Probabilistic Inference
We introduce a new approach to solving path-finding problems under uncertainty by representing them as probabilistic models and applying domain-independent inference algorithms to the models.
Particle Gibbs with Ancestor Sampling for Probabilistic Programs
Particle Markov chain Monte Carlo techniques rank among current state-of-the-art methods for probabilistic program inference.
Output-Sensitive Adaptive Metropolis-Hastings for Probabilistic Programs
We introduce an adaptive output-sensitive Metropolis-Hastings algorithm for probabilistic models expressed as programs, Adaptive Lightweight Metropolis-Hastings (AdLMH).
Asynchronous Anytime Sequential Monte Carlo
We introduce a new sequential Monte Carlo algorithm we call the particle cascade.
Infinite Structured Hidden Semi-Markov Models
This paper reviews recent advances in Bayesian nonparametric techniques for constructing and performing inference in infinite hidden Markov models.
A Compilation Target for Probabilistic Programming Languages
Forward inference techniques such as sequential Monte Carlo and particle Markov chain Monte Carlo for probabilistic programming can be implemented in any programming language by creative use of standardized operating system functionality including processes, forking, mutexes, and shared memory.
Tempering by Subsampling
In this paper we demonstrate that tempering Markov chain Monte Carlo samplers for Bayesian models by recursively subsampling observations without replacement can improve the performance of baseline samplers in terms of effective sample size per computation.
Hierarchically-coupled hidden Markov models for learning kinetic rates from single-molecule data
We address the problem of analyzing sets of noisy time-varying signals that all report on the same process but confound straightforward analyses due to complex inter-signal heterogeneities and measurement artifacts.
Inferring Team Strengths Using a Discrete Markov Random Field
We propose an original model for inferring team strengths using a Markov Random Field, which can be used to generate historical estimates of the offensive and defensive strengths of a team over time.
Hierarchically Supervised Latent Dirichlet Allocation
We introduce hierarchically supervised latent Dirichlet allocation (HSLDA), a model for hierarchically and multiply labeled bag-of-word data.
Probabilistic Deterministic Infinite Automata
We suggest that our method for averaging over PDFAs is a novel approach to predictive distribution smoothing.
Characterizing neural dependencies with copula models
The coding of information by neural populations depends critically on the statistical dependencies between neuronal responses.
Dependent Dirichlet Process Spike Sorting
In this paper we propose a new incremental spike sorting model that automatically eliminates refractory period violations, accounts for action potential waveform drift, and can handle appearance" and "disappearance" of neurons.
