Search Results for author:
Found 51 papers, 32 papers with code
Diffusion Models as Cartoonists! The Curious Case of High Density Regions
We investigate what kind of images lie in the high-density regions of diffusion models.
Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra Costs
The covariance for clean data given a noisy observation is an important quantity in many conditional generation methods for diffusion models.
What Ails Generative Structure-based Drug Design: Too Little or Too Much Expressivity?
Several generative models with elaborate training and sampling procedures have been proposed recently to accelerate structure-based drug design (SBDD); however, perplexingly, their empirical performance turns out to be suboptimal.
Improving robustness to corruptions with multiplicative weight perturbations
Deep neural networks (DNNs) excel on clean images but struggle with corrupted ones.
Robust Classification by Coupling Data Mollification with Label Smoothing
Introducing training-time augmentations is a key technique to enhance generalization and prepare deep neural networks against test-time corruptions.
Improving Discrete Diffusion Models via Structured Preferential Generation
In the domains of image and audio, diffusion models have shown impressive performance.
Alignment is Key for Applying Diffusion Models to Retrosynthesis
Retrosynthesis, the task of identifying precursors for a given molecule, can be naturally framed as a conditional graph generation task.
ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs
Climate and weather prediction traditionally relies on complex numerical simulations of atmospheric physics.
Field-based Molecule Generation
This work introduces FMG, a field-based model for drug-like molecule generation.
From Alexnet to Transformers: Measuring the Non-linearity of Deep Neural Networks with Affine Optimal Transport
In the last decade, we have witnessed the introduction of several novel deep neural network (DNN) architectures exhibiting ever-increasing performance across diverse tasks.
Learning Space-Time Continuous Neural PDEs from Partially Observed States
We introduce a novel grid-independent model for learning partial differential equations (PDEs) from noisy and partial observations on irregular spatiotemporal grids.
Input-gradient space particle inference for neural network ensembles
To sidestep these difficulties, we propose First-order Repulsive Deep Ensemble (FoRDE), an ensemble learning method based on ParVI, which performs repulsion in the space of first-order input gradients.
AbODE: Ab Initio Antibody Design using Conjoined ODEs
Antibodies are Y-shaped proteins that neutralize pathogens and constitute the core of our adaptive immune system.
Learning representations that are closed-form Monge mapping optimal with application to domain adaptation
Optimal transport (OT) is a powerful geometric tool used to compare and align probability measures following the least effort principle.
Uncertainty-Aware Natural Language Inference with Stochastic Weight Averaging
This paper introduces Bayesian uncertainty modeling using Stochastic Weight Averaging-Gaussian (SWAG) in Natural Language Understanding (NLU) tasks.
Learning Energy Conserving Dynamics Efficiently with Hamiltonian Gaussian Processes
Hamiltonian mechanics is one of the cornerstones of natural sciences.
Continuous-Time Functional Diffusion Processes
We introduce Functional Diffusion Processes (FDPs), which generalize score-based diffusion models to infinite-dimensional function spaces.
Ranked #26 on
Image Generation
on CelebA 64x64
Modular Flows: Differential Molecular Generation
Generating new molecules is fundamental to advancing critical applications such as drug discovery and material synthesis.
Latent Neural ODEs with Sparse Bayesian Multiple Shooting
Training dynamic models, such as neural ODEs, on long trajectories is a hard problem that requires using various tricks, such as trajectory splitting, to make model training work in practice.
Incorporating functional summary information in Bayesian neural networks using a Dirichlet process likelihood approach
We present a simple approach to incorporate prior knowledge in BNNs based on external summary information about the predicted classification probabilities for a given dataset.
Generative Modelling With Inverse Heat Dissipation
While diffusion models have shown great success in image generation, their noise-inverting generative process does not explicitly consider the structure of images, such as their inherent multi-scale nature.
Tackling covariate shift with node-based Bayesian neural networks
In this paper, we interpret these latent noise variables as implicit representations of simple and domain-agnostic data perturbations during training, producing BNNs that perform well under covariate shift due to input corruptions.
De-randomizing MCMC dynamics with the diffusion Stein operator
Parallel to LD, Stein variational gradient descent (SVGD) similarly minimizes the KL, albeit endowed with a novel Stein-Wasserstein distance, by deterministically transporting a set of particle samples, thus de-randomizes the stochastic diffusion process.
Enforcing physics-based algebraic constraints for inference of PDE models on unstructured grids
Data-driven neural network models have recently shown great success in modelling and learning complex PDE systems.
Evolving-Graph Gaussian Processes
Graph Gaussian Processes (GGPs) provide a data-efficient solution on graph structured domains.
Variational multiple shooting for Bayesian ODEs with Gaussian processes
Recent machine learning advances have proposed black-box estimation of unknown continuous-time system dynamics directly from data.
Affine Transport for Sim-to-Real Domain Adaptation
In this paper, we present affine transport -- a variant of optimal transport, which models the mapping between state transition distributions between the source and target domains with an affine transformation.
Continuous-Time Model-Based Reinforcement Learning
Model-based reinforcement learning (MBRL) approaches rely on discrete-time state transition models whereas physical systems and the vast majority of control tasks operate in continuous-time.
Model-based Reinforcement Learning
reinforcement-learning
+2
Sample-efficient reinforcement learning using deep Gaussian processes
In model-based reinforcement learning efficiency is improved by learning to simulate the world dynamics.
Scalable Bayesian neural networks by layer-wise input augmentation
We introduce implicit Bayesian neural networks, a simple and scalable approach for uncertainty representation in deep learning.
Bayesian Inference for Optimal Transport with Stochastic Cost
In machine learning and computer vision, optimal transport has had significant success in learning generative models and defining metric distances between structured and stochastic data objects, that can be cast as probability measures.
Likelihood-Free Inference with Deep Gaussian Processes
In recent years, surrogate models have been successfully used in likelihood-free inference to decrease the number of simulator evaluations.
Learning continuous-time PDEs from sparse data with graph neural networks
We demonstrate the model's ability to work with unstructured grids, arbitrary time steps, and noisy observations.
Sparse Gaussian Processes Revisited: Bayesian Approaches to Inducing-Variable Approximations
Variational inference techniques based on inducing variables provide an elegant framework for scalable posterior estimation in Gaussian process (GP) models.
ODE2VAE: Deep generative second order ODEs with Bayesian neural networks
We present Ordinary Differential Equation Variational Auto-Encoder (ODE2VAE), a latent second order ODE model for high-dimensional sequential data.
ODE$^2$VAE: Deep generative second order ODEs with Bayesian neural networks
We present Ordinary Differential Equation Variational Auto-Encoder (ODE$^2$VAE), a latent second order ODE model for high-dimensional sequential data.
Ranked #1 on
Video Prediction
on CMU Mocap-1
Learning spectrograms with convolutional spectral kernels
We introduce the convolutional spectral kernel (CSK), a novel family of non-stationary, nonparametric covariance kernels for Gaussian process (GP) models, derived from the convolution between two imaginary radial basis functions.
Neural Non-Stationary Spectral Kernel
Spectral mixture kernels have been proposed as general-purpose, flexible kernels for learning and discovering more complicated patterns in the data.
Harmonizable mixture kernels with variational Fourier features
The expressive power of Gaussian processes depends heavily on the choice of kernel.
Deep learning with differential Gaussian process flows
We propose a novel deep learning paradigm of differential flows that learn a stochastic differential equation transformations of inputs prior to a standard classification or regression function.
Deep convolutional Gaussian processes
We propose deep convolutional Gaussian processes, a deep Gaussian process architecture with convolutional structure.
Learning Stochastic Differential Equations With Gaussian Processes Without Gradient Matching
We introduce a novel paradigm for learning non-parametric drift and diffusion functions for stochastic differential equation (SDE).
Bayesian Metabolic Flux Analysis reveals intracellular flux couplings
Flux analysis methods commonly place unrealistic assumptions on fluxes due to the convenience of formulating the problem as a linear programming model, and most methods ignore the notable uncertainty in flux estimates.
Variational zero-inflated Gaussian processes with sparse kernels
We propose a novel model family of zero-inflated Gaussian processes (ZiGP) for such zero-inflated datasets, produced by sparse kernels through learning a latent probit Gaussian process that can zero out kernel rows and columns whenever the signal is absent.
Learning unknown ODE models with Gaussian processes
In conventional ODE modelling coefficients of an equation driving the system state forward in time are estimated.
mGPfusion: Predicting protein stability changes with Gaussian process kernel learning and data fusion
We introduce a Bayesian data fusion model that re-calibrates the experimental and in silico data sources and then learns a predictive GP model from the combined data.
Non-Stationary Spectral Kernels
We propose non-stationary spectral kernels for Gaussian process regression.
A Mutually-Dependent Hadamard Kernel for Modelling Latent Variable Couplings
We introduce a novel kernel that models input-dependent couplings across multiple latent processes.
Random Fourier Features for Operator-Valued Kernels
Devoted to multi-task learning and structured output learning, operator-valued kernels provide a flexible tool to build vector-valued functions in the context of Reproducing Kernel Hilbert Spaces.
Non-Stationary Gaussian Process Regression with Hamiltonian Monte Carlo
We present a novel approach for fully non-stationary Gaussian process regression (GPR), where all three key parameters -- noise variance, signal variance and lengthscale -- can be simultaneously input-dependent.
Learning nonparametric differential equations with operator-valued kernels and gradient matching
Modeling dynamical systems with ordinary differential equations implies a mechanistic view of the process underlying the dynamics.
