arXiv research

AF improves sampling from high-dimensional, multi-modal distributions.

ROME improves density estimation for multi-modal, non-normal data.

Piecewise normalizing flows improve multi-modal distribution modeling.

DiGS improves sampling from multi-modal distributions.

New method trains neural samplers to sample from multi-modal distributions efficiently.

Diffusion models learn multi-modal distributions with optimal efficiency.

New method samples from multi-modal distributions on Riemannian manifolds without training.

Develops multi-modal neural network models for improved prediction and uncertainty quantification.

A new algorithm flattens multi-modal distributions for better deep learning.

The paper improves SMC algorithm for multi-modal distributions by proving variance bounds.

New divergences improve score-based methods for multi-modal distributions.

New framework shows cross-attention improves multi-modal in-context learning.

The Hamiltonian Monte Carlo (HMC) sampling algorithm exploits Hamiltonian dynamics to construct efficient Markov Chain Monte Carlo (MCMC), which has become increasingly popular in machine learning and statistics. Since HMC uses the gradient information of the target distribution, it can explore the state space much mor…

A new method samples from multi-modal distributions without hyperparameter tuning.

Contrastive learning adapts to data intrinsic dimensions, learning low-dimensional representations.

FlowVAT improves variational inference for multi-modal distributions.

Framework for handling long-tailed multi-modal data.

Improved PDMP samplers for multi-modal distributions using tempering.

Prediction of future states of the environment and interacting agents is a key competence required for autonomous agents to operate successfully in the real world. Prior work for structured sequence prediction based on latent variable models imposes a uni-modal standard Gaussian prior on the latent variables. This indu…

Sampling from posterior distributions using Markov chain Monte Carlo (MCMC) methods can require an exhaustive number of iterations, particularly when the posterior is multi-modal as the MCMC sampler can become trapped in a local mode for a large number of iterations. In this paper, we introduce the pseudo-extended MCMC…

This work improves multi-modal generative models by using permutation-invariant neural networks.

A new method for Gaussian filtering using gradient flows and Wasserstein metrics.

A key task in Bayesian statistics is sampling from distributions that are only specified up to a partition function (i.e., constant of proportionality). However, without any assumptions, sampling (even approximately) can be #P-hard, and few works have provided "beyond worst-case" guarantees for such settings. For log-c…

GACEM optimizes complex multi-modal problems using neural networks.

This work tackles uncertainty in multi-agent multi-modal trajectory forecasting.

This paper uses robust optimization to analyze supply chain resilience.

C-qGAN learns multi-modal distributions efficiently.

This paper rates robustness of multi-modal time-series forecasting models.

Boltzmann machines are undirected graphical models with two-state stochastic variables, in which the logarithms of the clique potentials are quadratic functions of the node states. They have been widely studied in the neural computing literature, although their practical applicability has been limited by the difficulty…

The paper analyzes and proposes an algorithm for multi-modal nonlinear embeddings with theoretical performance bounds.

This paper improves non-asymptotic bounds for denoising diffusions, focusing on the Ornstein-Uhlenbeck process.

Over the past years, Generative Adversarial Networks (GANs) have shown a remarkable generation performance especially in image synthesis. Unfortunately, they are also known for having an unstable training process and might loose parts of the data distribution for heterogeneous input data. In this paper, we propose a no…

Geometric tempering fails for Langevin dynamics, proving convergence limits.

Proposes CE-BASS for robust Kalman filtering with innovative and additive outliers.

Paper develops a theory explaining contrastive pre-training for multimodal AI.

MoCA uses a novel autoencoder to analyze multi-modal health data.

This paper introduces NPR, a technique to improve Bayesian inference for multi-modal, high-dimensional simulations.

The paper evaluates samplers on multi-modal targets, focusing on mode separation and recovery.

Predicting human behavior is a difficult and crucial task required for motion planning. It is challenging in large part due to the highly uncertain and multi-modal set of possible outcomes in real-world domains such as autonomous driving. Beyond single MAP trajectory prediction, obtaining an accurate probability distri…

This paper improves ensemble learning for vision tasks by encouraging diversity in predictions.

New model improves MCMC efficiency and multi-modal distribution exploration.

Two-stage framework detects multi-modal outliers.

New methods for Bayesian inference using mean shift particle systems.

A new depth measure based on optimal control theory captures multi-modal data.

This work incorporates the multi-modality of the data distribution into a Gaussian Process regression model. We approach the problem from a discriminative perspective by learning, jointly over the training data, the target space variance in the neighborhood of a certain sample through metric learning. We start by using…

A new Monte Carlo sampling method derived from reverse diffusion.

In this paper, we propose a novel maximum causal Tsallis entropy (MCTE) framework for imitation learning which can efficiently learn a sparse multi-modal policy distribution from demonstrations. We provide the full mathematical analysis of the proposed framework. First, the optimal solution of an MCTE problem is shown …

Diffusion models enhance robotic manipulation through probabilistic multi-modal learning.