Search Results for author:
Found 48 papers, 18 papers with code
VISA: Variational Inference with Sequential Sample-Average Approximations
We present variational inference with sequential sample-average approximation (VISA), a method for approximate inference in computationally intensive models, such as those based on numerical simulations.
Towards Reducing Diagnostic Errors with Interpretable Risk Prediction
In this work we propose a method to use LLMs to identify pieces of evidence in patient EHR data that indicate increased or decreased risk of specific diagnoses; our ultimate aim is to increase access to evidence and reduce diagnostic errors.
Topological Obstructions and How to Avoid Them
Incorporating geometric inductive biases into models can aid interpretability and generalization, but encoding to a specific geometric structure can be challenging due to the imposed topological constraints.
One-shot Imitation Learning via Interaction Warping
We propose a new method, Interaction Warping, for learning SE(3) robotic manipulation policies from a single demonstration.
String Diagrams with Factorized Densities
A growing body of research on probabilistic programs and causal models has highlighted the need to reason compositionally about model classes that extend directed graphical models.
CHiLL: Zero-shot Custom Interpretable Feature Extraction from Clinical Notes with Large Language Models
We propose CHiLL (Crafting High-Level Latents), an approach for natural-language specification of features for linear models.
Verified Reversible Programming for Verified Lossless Compression
Agda supports formal verification of program properties, and the compiler for our reversible language (which is implemented as an Agda macro), produces not just an encoder/decoder pair of functions but also a proof that they are inverse to one another.
A Variational Perspective on Generative Flow Networks
Generative flow networks (GFNs) are a class of models for sequential sampling of composite objects, which approximate a target distribution that is defined in terms of an energy function or a reward.
That's the Wrong Lung! Evaluating and Improving the Interpretability of Unsupervised Multimodal Encoders for Medical Data
We compare alignments from a state-of-the-art multimodal (image and text) model for EHR with human annotations that link image regions to sentences.
Deriving time-averaged active inference from control principles
Active inference offers a principled account of behavior as minimizing average sensory surprise over time.
Binding Actions to Objects in World Models
We study the problem of binding actions to objects in object-factored world models using action-attention mechanisms.
Factored World Models for Zero-Shot Generalization in Robotic Manipulation
In this paper, we learn to generalize over robotic pick-and-place tasks using object-factored world models, which combat the combinatorial explosion by ensuring that predictions are equivariant to permutations of objects.
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.
Learning Symmetric Representations for Equivariant World Models
In this paper, we use equivariant transition models as an inductive bias to learn symmetric latent representations in a self-supervised manner.
Conjugate Energy-Based Models
In this paper, we propose conjugate energy-based models (CEBMs), a new class of energy-based models that define a joint density over data and latent variables.
Nested Variational Inference
We develop nested variational inference (NVI), a family of methods that learn proposals for nested importance samplers by minimizing an forward or reverse KL divergence at each level of nesting.
Disentangling Representations of Text by Masking Transformers
Representations from large pretrained models such as BERT encode a range of features into monolithic vectors, affording strong predictive accuracy across a multitude of downstream tasks.
On the Impact of Random Seeds on the Fairness of Clinical Classifiers
Recent work has shown that fine-tuning large networks is surprisingly sensitive to changes in random seed(s).
Learning Proposals for Probabilistic Programs with Inference Combinators
Proposals in these samplers can be parameterized using neural networks, which in turn can be trained by optimizing variational objectives.
Generator Surgery for Compressed Sensing
We introduce a method for achieving low representation error using generators as signal priors.
Action Priors for Large Action Spaces in Robotics
This paper proposes an alternative approach where the solutions of previously solved tasks are used to produce an action prior that can facilitate exploration in future tasks.
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.
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)
Query-Focused EHR Summarization to Aid Imaging Diagnosis
We propose and evaluate models that extract relevant text snippets from patient records to provide a rough case summary intended to aid physicians considering one or more diagnoses.
Deep Markov Spatio-Temporal Factorization
This results in a flexible family of hierarchical deep generative factor analysis models that can be extended to perform time series clustering or perform factor analysis in the presence of a control signal.
Learning Discrete State Abstractions With Deep Variational Inference
In this work, we propose an information bottleneck method for learning approximate bisimulations, a type of state abstraction.
Rate-Regularization and Generalization in VAEs
Variational autoencoders optimize an objective that combines a reconstruction loss (the distortion) and a KL term (the rate).
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.
Neural Topographic Factor Analysis for fMRI Data
Neuroimaging studies produce gigabytes of spatio-temporal data for a small number of participants and stimuli.
Can VAEs Generate Novel Examples?
This leads to the hypothesis that, for a sufficiently high capacity encoder and decoder, the VAE decoder will perform nearest-neighbor matching according to the coordinates in the latent space.
Structured Neural Topic Models for Reviews
We present Variational Aspect-based Latent Topic Allocation (VALTA), a family of autoencoding topic models that learn aspect-based representations of reviews.
Nested Reasoning About Autonomous Agents Using Probabilistic Programs
As autonomous agents become more ubiquitous, they will eventually have to reason about the plans of other agents, which is known as theory of mind reasoning.
Composing Modeling and Inference Operations with Probabilistic Program Combinators
We assume that models are dynamic, but that model composition is static, in the sense that combinator application takes place prior to evaluating the model on data.
On Exploration, Exploitation and Learning in Adaptive Importance Sampling
We study adaptive importance sampling (AIS) as an online learning problem and argue for the importance of the trade-off between exploration and exploitation in this adaptation.
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.
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.
Learning Disentangled Representations of Texts with Application to Biomedical Abstracts
We propose a method for learning disentangled representations of texts that code for distinct and complementary aspects, with the aim of affording efficient model transfer and interpretability.
Structured Disentangled Representations
Deep latent-variable models learn representations of high-dimensional data in an unsupervised manner.
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.
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.
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.
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.
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.
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.
Stylistic Clusters and the Syrian/South Syrian Tradition of First-Millennium BCE Levantine Ivory Carving: A Machine Learning Approach
Thousands of first-millennium BCE ivory carvings have been excavated from Neo-Assyrian sites in Mesopotamia (primarily Nimrud, Khorsabad, and Arslan Tash) hundreds of miles from their Levantine production contexts.
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.
