Search Results for author:
Found 20 papers, 14 papers with code
Involutive MCMC: One Way to Derive Them All
Markov Chain Monte Carlo (MCMC) is a computational approach to fundamental problems such as inference, integration, optimization, and simulation.
Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts
While score-based generative models are the model of choice across diverse domains, there are limited tools available for controlling inference-time behavior in a principled manner, e. g. for composing multiple pretrained models.
The Superposition of Diffusion Models Using the Itô Density Estimator
The Cambrian explosion of easily accessible pre-trained diffusion models suggests a demand for methods that combine multiple different pre-trained diffusion models without incurring the significant computational burden of re-training a larger combined model.
Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling
Rare event sampling in dynamical systems is a fundamental problem arising in the natural sciences, which poses significant computational challenges due to an exponentially large space of trajectories.
Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold
Flow-based models allow for learning these dynamics at the population level - they model the evolution of the entire distribution of samples.
Efficient Evolutionary Search Over Chemical Space with Large Language Models
Molecular discovery, when formulated as an optimization problem, presents significant computational challenges because optimization objectives can be non-differentiable.
Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints
To constrain the optimization process to the data manifold, we reformulate the original optimization problem as a sampling problem from the product of the Boltzmann distribution defined by the objective function and the data distribution learned by the diffusion model.
Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC
Second-order methods such as KFAC can be useful for neural net training.
A Computational Framework for Solving Wasserstein Lagrangian Flows
The dynamical formulation of the optimal transport can be extended through various choices of the underlying geometry (kinetic energy), and the regularization of density paths (potential energy).
Quantum HyperNetworks: Training Binary Neural Networks in Quantum Superposition
Binary neural networks, i. e., neural networks whose parameters and activations are constrained to only two possible values, offer a compelling avenue for the deployment of deep learning models on energy- and memory-limited devices.
Action Matching: Learning Stochastic Dynamics from Samples
Learning the continuous dynamics of a system from snapshots of its temporal marginals is a problem which appears throughout natural sciences and machine learning, including in quantum systems, single-cell biological data, and generative modeling.
Particle Dynamics for Learning EBMs
We accomplish this by viewing the evolution of the modeling distribution as (i) the evolution of the energy function, and (ii) the evolution of the samples from this distribution along some vector field.
Deterministic Gibbs Sampling via Ordinary Differential Equations
Deterministic dynamics is an essential part of many MCMC algorithms, e. g.
Orbital MCMC
Markov Chain Monte Carlo (MCMC) algorithms ubiquitously employ complex deterministic transformations to generate proposal points that are then filtered by the Metropolis-Hastings-Green (MHG) test.
Involutive MCMC: a Unifying Framework
Markov Chain Monte Carlo (MCMC) is a computational approach to fundamental problems such as inference, integration, optimization, and simulation.
The Implicit Metropolis-Hastings Algorithm
For any implicit probabilistic model and a target distribution represented by a set of samples, implicit Metropolis-Hastings operates by learning a discriminator to estimate the density-ratio and then generating a chain of samples.
Metropolis-Hastings view on variational inference and adversarial training
From this point of view, the problem of constructing a sampler can be reduced to the question - how to choose a proposal for the MH algorithm?
Variance Networks: When Expectation Does Not Meet Your Expectations
Ordinary stochastic neural networks mostly rely on the expected values of their weights to make predictions, whereas the induced noise is mostly used to capture the uncertainty, prevent overfitting and slightly boost the performance through test-time averaging.
Uncertainty Estimation via Stochastic Batch Normalization
In this work, we investigate Batch Normalization technique and propose its probabilistic interpretation.
Structured Bayesian Pruning via Log-Normal Multiplicative Noise
In the paper, we propose a new Bayesian model that takes into account the computational structure of neural networks and provides structured sparsity, e. g. removes neurons and/or convolutional channels in CNNs.
