arXiv Machine Learning
Jun 16
Not all Jensen-Shannon Divergence Estimators are Equal
arXiv:2606. 16411v1 Announce Type: new Abstract: The Jensen-Shannon divergence is widely reported as a scalar measure of fidelity for synthetic tabular data.
Approximating $f$-Divergences with Rank Statistics
arXiv:2601. 22784v2 Announce Type: replace-cross Abstract: We introduce a rank-statistic approximation of $f$-divergences that avoids explicit density-ratio estimation by working directly with the distribution of ranks.
Related stories
arXiv Machine Learning
Jun 30
Highly Data Parallelizable Estimation of the Sliced-Wasserstein Distance Using Cumulative Distribution Functions
arXiv:2606. 30310v1 Announce Type: cross Abstract: The Sliced Wasserstein (SW) distance has emerged as a computationally attractive alternative to the Wasserstein distance by leveraging one-dimensional optimal transport along random projections.
arXiv Machine Learning
Jul 28
Minimax Lower Bounds of Kernel Discrepancy Estimation: MMD, HSIC, KSD
arXiv:2607. 24235v1 Announce Type: cross Abstract: Over the past 20 years, kernel discrepancies have been leveraged as a highly powerful tool for quantifying the disagreement of distributions, with numerous successful applications in two-sample, goodness-of-fit, and independence testing, among others.
arXiv AI
Jun 16
Variance Reduction for Non-Log-Concave Sampling with Applications to Inverse Problems
arXiv:2606. 16257v1 Announce Type: cross Abstract: Sampling from high-dimensional, non-log-concave distributions with unnormalized densities is a fundamental challenge in machine learning, particularly when the exact gradient of the potential is unavailable and must be approximated via stochastic gradients that exhibit high variance under a fixed budget of gradient computations per iteration.
arXiv Machine Learning
2d ago
High-dimensional nonparametric changepoint detection via low-rank degree-two density projection
arXiv:2608. 13922v1 Announce Type: new Abstract: Detecting distributional changes in high dimension is difficult when neither the pre-change nor post-change density is parametrically specified.
arXiv Machine Learning
Jul 23
Directional Kernel Mean Difference: A Fast Signed Statistic for Univariate Distribution Comparison
arXiv:2607. 20119v1 Announce Type: cross Abstract: We introduce the Directional Kernel Mean Difference (DKMD), a signed statistic for univariate distribution comparison that preserves the direction of distributional shifts.
arXiv Machine Learning
Aug 3
Statistical Inference for Stochastic Gradient Descent: Beyond Finite Variance
arXiv:2605. 26000v2 Announce Type: replace-cross Abstract: Stochastic gradient descent (SGD) is foundational to large-scale statistical learning and stochastic optimization.
arXiv Machine Learning
Jun 30
Concentration bounds on response-based vector embeddings of black-box generative models
arXiv:2511. 08307v2 Announce Type: replace-cross Abstract: Generative models, such as large language models or text-to-image diffusion models, can generate relevant responses to user-given queries.
arXiv Machine Learning
Aug 4
Nonparametric Distribution Regression Re-calibration
arXiv:2602. 13362v2 Announce Type: replace-cross Abstract: A key challenge in probabilistic regression is ensuring that predictive distributions accurately reflect true empirical uncertainty.
arXiv Machine Learning
Jun 5
Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
arXiv:2606. 06179v1 Announce Type: cross Abstract: Score-based diffusion models are typically trained by minimizing the $L^2$ score matching error, and standard theoretical analyses rely on this quantity to bound the sampling discrepancy between the learned and target distributions.
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 28
Efficient Learning of Truncated Boolean Product Distributions: Influence to the Rescue
arXiv:2607. 22889v1 Announce Type: new Abstract: Learning the natural parameters $z \in \mathbb{R}^n$ of discrete distributions $\mu_z$ from independent samples constrained to a subset $S \subseteq \{0,1\}^n$ is a foundational challenge in high-dimensional statistics.