arXiv Machine Learning
Jul 2
Accelerating Discrete Diffusion Models with Parallel-In-Time Sampling
arXiv:2607. 00773v1 Announce Type: new Abstract: Discrete diffusion models are widely used for learning and generating discrete distributions.
Efficient Sampling with Discrete Diffusion Models: Sharp and Adaptive Guarantees
arXiv:2602. 15008v2 Announce Type: replace Abstract: Diffusion models over discrete spaces have recently shown striking empirical success, yet their theoretical foundations remain incomplete.
Related stories
arXiv Machine Learning
Jul 30
Denoising growth complexity: Data geometry and certified schedules for diffusion sampling
arXiv:2607. 26285v1 Announce Type: cross Abstract: Two central challenges in diffusion-based sampling are the theoretical one of understanding their remarkable effectiveness even in high-dimensional settings, and the practical one of designing algorithms with certified performance guarantees.
arXiv Machine Learning
Jul 2
Fast Score-Based Sampling via Log-Concave Reductions
arXiv:2512. 24152v2 Announce Type: replace-cross Abstract: Sampling based on score diffusions has led to striking empirical results, and has attracted considerable attention from various research communities.
arXiv AI
6d ago
The data geometry of masking diffusion: Certified-optimal schedules via unmasking growth complexity
arXiv:2608. 13520v1 Announce Type: cross Abstract: We study masking diffusion for discrete sampling and introduce a path-resolved measure of data geometry called the \emph{unmasking growth complexity} ({\textsf{UGC}\xspace}).
arXiv Machine Learning
Jun 18
Dimension-Free Convergence of Discrete Diffusion Models: Adjoint Equations Induce the Right Space
arXiv:2605. 17232v2 Announce Type: replace Abstract: Discrete diffusion has become a leading framework for generative modeling in various applications including language, vision, and biology.
arXiv Machine Learning
Jul 14
Low-dimensional adaptation of diffusion models: Convergence in total variation
arXiv:2501. 12982v3 Announce Type: replace-cross Abstract: This paper investigates how diffusion generative models leverage (unknown) low-dimensional structure to accelerate sampling.
arXiv Machine Learning
Jul 9
Fast determinantal sampling on general spaces and diffusion geometry
arXiv:2607. 06644v1 Announce Type: cross Abstract: Determinantal point processes have recently emerged as a kernel-based alternative to standard independent sampling for constructing efficient minibatches, coresets, and other compact representations of large-scale datasets.
arXiv AI
Jul 14
Efficient Online Proportional Sampling with Applications to Smoothed Online Learning
arXiv:2607. 10963v1 Announce Type: cross Abstract: We study the problem of efficient online proportional sampling from a high-dimensional domain under a $\sigma$-smoothed adversary, where the sampling distribution is induced by a dynamically evolving weight function defined over a sequence of piecewise-structured partitions.
arXiv Machine Learning
2d ago
A Banach-Space Theory of Markovian Halpern Iteration for Non-Expansive Maps
arXiv:2608. 15966v1 Announce Type: new Abstract: We study stochastic approximation of fixed points of a non-expansive operator when the oracle samples originate from a continuing Markovian trajectory.
arXiv Machine Learning
Jun 24
A Time-Reparameterized Cumulative Intensity Extrapolation Sampler for Discrete Flow Matching
arXiv:2606. 24140v1 Announce Type: new Abstract: Discrete flow matching (DFM) provides a principled framework for generative modeling on discrete state spaces via continuous-time Markov chain dynamics.
arXiv Machine Learning
Jun 2
Consistent Diffusion Language Models
arXiv:2605. 00161v2 Announce Type: replace Abstract: Diffusion language models (DLMs) are an attractive alternative to autoregressive models because they promise sublinear-time, parallel generation, yet practical gains remain elusive as high-quality samples still demand hundreds of refinement steps.
arXiv Machine Learning
Jun 9
Wedge Sampling: Efficient Tensor Completion with Nearly-Linear Sample Complexity
arXiv:2602. 05869v2 Announce Type: replace-cross Abstract: We introduce Wedge Sampling, a new non-adaptive sampling scheme for low-rank tensor completion.