Search Results for author:
Found 28 papers, 11 papers with code
Position Paper: Bayesian Deep Learning in the Age of Large-Scale AI
In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets.
Modelling Cellular Perturbations with the Sparse Additive Mechanism Shift Variational Autoencoder
For example, in drug discovery, there is a need to model the effects of diverse interventions on cells in order to characterize unknown biological mechanisms of action.
Compositional Deep Probabilistic Models of DNA Encoded Libraries
DNA-Encoded Library (DEL) has proven to be a powerful tool that utilizes combinatorially constructed small molecules to facilitate highly-efficient screening assays.
Channel Vision Transformers: An Image Is Worth C x 16 x 16 Words
We evaluate the performance of ChannelViT on ImageNet, JUMP-CP (microscopy cell imaging), and So2Sat (satellite imaging).
Contextual Vision Transformers for Robust Representation Learning
Additionally, we introduce a context inference network to predict such tokens on-the-fly, given a batch of samples from the group.
DEL-Dock: Molecular Docking-Enabled Modeling of DNA-Encoded Libraries
Computational models have been deployed to learn the latent binding affinities that are correlated to the sequenced count data; however, this correlation is often obfuscated by various sources of noise introduced in its complicated data-generation process.
Black-box Coreset Variational Inference
Recent advances in coreset methods have shown that a selection of representative datapoints can replace massive volumes of data for Bayesian inference, preserving the relevant statistical information and significantly accelerating subsequent downstream tasks.
TyXe: Pyro-based Bayesian neural nets for Pytorch
We introduce TyXe, a Bayesian neural network library built on top of Pytorch and Pyro.
Revisiting Linear Decision Boundaries for Few-Shot Learning with Transformer Hypernetworks
Few-shot learning (FSL) methods aim to generalize a model to new unseen classes using only a small number of support examples.
Localized Uncertainty Attacks
Under this threat model, we create adversarial examples by perturbing only regions in the inputs where a classifier is uncertain.
Stochastic Aggregation in Graph Neural Networks
Graph neural networks (GNNs) manifest pathologies including over-smoothing and limited discriminating power as a result of suboptimally expressive aggregating mechanisms.
Variational Auto-Regressive Gaussian Processes for Continual Learning
Through sequential construction of posteriors on observing data online, Bayes' theorem provides a natural framework for continual learning.
Hierarchical Gaussian Process Priors for Bayesian Neural Network Weights
Probabilistic neural networks are typically modeled with independent weight priors, which do not capture weight correlations in the prior and do not provide a parsimonious interface to express properties in function space.
Generalized Hidden Parameter MDPs Transferable Model-based RL in a Handful of Trials
There is broad interest in creating RL agents that can solve many (related) tasks and adapt to new tasks and environments after initial training.
Gaussian Process Meta-Representations For Hierarchical Neural Network Weight Priors
Bayesian inference offers a theoretically grounded and general way to train neural networks and can potentially give calibrated uncertainty.
Gaussian Process Meta-Representations Of Neural Networks
Bayesian inference offers a theoretically grounded and general way to train neural networks and can potentially give calibrated uncertainty.
Applying SVGD to Bayesian Neural Networks for Cyclical Time-Series Prediction and Inference
A regression-based BNN model is proposed to predict spatiotemporal quantities like hourly rider demand with calibrated uncertainties.
Efficient transfer learning and online adaptation with latent variable models for continuous control
Traditional model-based RL relies on hand-specified or learned models of transition dynamics of the environment.
Pyro: Deep Universal Probabilistic Programming
Pyro is a probabilistic programming language built on Python as a platform for developing advanced probabilistic models in AI research.
Probabilistic Meta-Representations Of Neural Networks
Existing Bayesian treatments of neural networks are typically characterized by weak prior and approximate posterior distributions according to which all the weights are drawn independently.
Pathwise Derivatives for Multivariate Distributions
We exploit the link between the transport equation and derivatives of expectations to construct efficient pathwise gradient estimators for multivariate distributions.
Likelihood-free inference with emulator networks
Approximate Bayesian Computation (ABC) provides methods for Bayesian inference in simulation-based stochastic models which do not permit tractable likelihoods.
Adversarial Message Passing For Graphical Models
A popular tool for learning implicit models are generative adversarial networks (GANs) which learn parameters of generators by fooling discriminators.
Conditional Similarity Networks
A main reason for this is that contradicting notions of similarities cannot be captured in a single space.
Knowledge Transfer with Medical Language Embeddings
Identifying relationships between concepts is a key aspect of scientific knowledge synthesis.
A Generative Model of Words and Relationships from Multiple Sources
We propose a generative model which integrates evidence from diverse data sources, enabling the sharing of semantic information.
Bayesian representation learning with oracle constraints
Representation learning systems typically rely on massive amounts of labeled data in order to be trained to high accuracy.
Automatic Relevance Determination For Deep Generative Models
A recurring problem when building probabilistic latent variable models is regularization and model selection, for instance, the choice of the dimensionality of the latent space.
