arXiv:2410. 13800v4 Announce Type: replace-cross Abstract: Physically motivated stochastic dynamics are widely used to sample from high-dimensional distributions.
arXiv:2607. 08303v1 Announce Type: new Abstract: The problem of learning constant-depth circuits holds profound implications for computational learning theory.
arXiv:2606. 30773v1 Announce Type: cross Abstract: We introduce a novel technique for scalable sampling of spin-system states with continuous symmetries using diffusion models.
arXiv:2608. 14408v1 Announce Type: cross Abstract: We study online statistical inference for functionals of the return distribution under a fixed policy.
arXiv:2511. 06239v2 Announce Type: replace-cross Abstract: Learning-based methods for sampling from the Gibbs distribution in finite-dimensional spaces have progressed quickly, yet theory and algorithmic design for infinite-dimensional function spaces remain limited.
arXiv:2608. 07648v1 Announce Type: cross Abstract: Sampling high-dimensional probability distributions is a central task in scientific computing, with applications ranging from Bayesian inference to statistical physics and molecular simulation.
arXiv:2608. 08644v1 Announce Type: new Abstract: We consider the problem of sampling compositional and discrete objects from a given unnormalized posterior distribution.
We consider the problem of sampling compositional and discrete objects from a given unnormalized posterior distribution. Notably, recent studies have shown that this problem can be efficiently solved by learning a deterministic Markov Decision Process (MDP) that progressively builds each object in proportion to the posterior.
arXiv:2603. 27996v2 Announce Type: replace Abstract: Diffusion models have emerged as a powerful framework for generative tasks in deep learning.
arXiv:2608. 01833v1 Announce Type: cross Abstract: Grokking is a striking phenomenon in neural network training, where a model can undergo a prolonged period of pure memorization before abrupt generalization.
arXiv:2606. 30064v1 Announce Type: new Abstract: We introduce a data-driven probabilistic framework for learning systems based on Gibbs measures on hierarchical structures.
We introduce a data-driven probabilistic framework for learning systems based on Gibbs measures on hierarchical structures. Unlike standard empirical risk minimization, where a dataset is used to identify a single optimal parameter, our approach transforms the empirical loss function into an interaction potential defining an energy-based model.
arXiv:2606. 18778v1 Announce Type: new Abstract: Online learning in non-stationary streams is often formulated as tracking a point estimate, but many applications require predicting the full data-generating distribution.