6 papers
Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps
RuiKang OuYang, Hanlin Yu, Xinyue Ai +7
Recent progress in flow-based generative modeling has led to models that output high-quality samples while using only a small number of function evaluations. However, at present, t…
Sampling from multi-modal distributions with polynomial query complexity in fixed dimension via reverse diffusion
Adrien Vacher, Omar Chehab, Anna Korba
Even in low dimensions, sampling from multi-modal distributions is challenging. We provide the first sampling algorithm for a broad class of distributions -- including all Gaussian…
Multi-View Causal Discovery without Non-Gaussianity: Identifiability and Algorithms
Ambroise Heurtebise, Omar Chehab, Pierre Ablin +2
Causal discovery is a difficult problem that typically relies on strong assumptions on the data-generating model, such as non-Gaussianity. In practice, many modern applications pro…
MVICAD2: Multi-View Independent Component Analysis with Delays and Dilations
Ambroise Heurtebise, Omar Chehab, Pierre Ablin +1
Machine learning techniques in multi-view settings face significant challenges, particularly when integrating heterogeneous data, aligning feature spaces, and managing view-specifi…
Density Ratio Estimation with Conditional Probability Paths
Hanlin Yu, Arto Klami, Aapo Hyvärinen +2
Density ratio estimation in high dimensions can be reframed as integrating a certain quantity, the time score, over probability paths which interpolate between the two densities. I…
Provable Convergence and Limitations of Geometric Tempering for Langevin Dynamics
Omar Chehab, Anna Korba, Austin Stromme +1
Geometric tempering is a popular approach to sampling from challenging multi-modal probability distributions by instead sampling from a sequence of distributions which interpolate,…