stat.ML · 2026-10-15 · No. 144
Machine Learning, 2026-10-15.
8 new papers in stat.ML. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
8 entries-
01
Posterior Frequencies and the Cost of Not Fitting: A Correction to a Memorization Lower Bound
Zhenisbek Assylbekov, Rustem Takhanov
stat.ML · cs.LG
Feldman's memorization lower bound assigns a frequency coefficient based on how often a point appears in the training sample. We give an exact three-point counterexample to its conditional and averaged forms, using independent fair labels and a permutation-equivariant learner. A sequence of sampling priors makes the ratio of the proposed penalty to actual excess risk grow exponentially, ruling out a universal positive constant-factor repair....
-
02
The minimal width of neural networks and immersions of real projective space
BaoZhi Chu, Ben Weinkove
stat.ML · cs.LG
We investigate the minimal width of deep neural networks that can approximate all continuous functions from $\mathbb{R}^n$ to $\mathbb{R}^m$ in the topology of uniform convergence on compact subsets. We show that whenever the real projective space $\mathbb{RP}^{n-1}$ admits a smooth immersion into $\mathbb{R}^n$, the minimal width is at least $n+\min\{n,m\}$, assuming that the activation function is continuous and monotone. As a consequence,...
-
03
Mixed Poisson diffusion models and application to posterior sampling
Thibaut Pellerin, Alain Durmus, Elinor Berger, Eric Barat
stat.ML · cs.LG · stat.CO
Diffusion models are a powerful framework for learning complex probability distributions. While widely used diffusion models for continuous data rely on Gaussian noising processes, we instead develop diffusion models based on Poisson noise. More precisely, we introduce and study a new mathematical framework, called Mixed Poisson Diffusion Models (MPDM), with noising dynamics driven by multivariate counting processes. Our methodology is...
-
04
Weighted Adjoint Matching: Finetuning Flow Matching Models with Time-Dependent Control Cost
Eliot Beyler, Francis Bach
stat.ML · cs.LG
We introduce Weighted Adjoint Matching, a method to finetune a pretrained diffusion or flow matching model given a differentiable reward. We derive it from Adjoint Matching, which reformulates finetuning as a stochastic optimal control problem with a quadratic control cost. Building on the observation that these models generate coarse features before fine details, we place a time-dependent weight on the control cost. A high cost early in the...
-
05
Minimax estimation of the pseudo-spectral gap of continuous Markov chains, with applications to empirical concentration bounds
Vahe Karagulyan, Mikołaj Kasprzak, Pierre Alquier
stat.ML · cs.LG · math.ST
We study the minimax estimation of the pseudo-spectral gap $γ_{ps}$ of a Markov chain from the observation of a single trajectory. Extending earlier works on finite-state space chains by Wolfer and Kontorovich (2024), we provide an estimator in the case of a compact, continuous state-space. Our estimator appears to be minimax-optimal on the class of chains with a transition operator with Lipschitz density, up to logarithmic terms. Our...
-
06
Convergence Rates of Gaussian Process Thompson Sampling for Efficient Global Optimization
Haowei Wang, Yilin Zheng
stat.ML · cs.LG
Efficient global optimization aims to identify a global optimum of an expensive black-box function within a limited evaluation budget $N$. We investigate the convergence rates of Gaussian process Thompson sampling (GP-TS) under noiseless observations, assuming a fixed objective function in a reproducing kernel Hilbert space (RKHS). For Matérn kernels with smoothness parameter $ν$ in dimension $d$, we establish a worst-case expected...
-
07
On the Optimisation Landscape of Overparameterised Weighted MMD
Tharrshann Jayan Logarajah, Jeremias Knoblauch, Louis Sharrock
stat.ML · cs.LG · math.OC
We study the optimisation landscape of the maximum mean discrepancy (MMD) over weighted atomic measures. For the one-dimensional Gaussian kernel, we show that, for any compactly supported target distribution, sufficiently many particles ensure that every local minimum has arbitrarily small MMD. Moreover, any stationary point whose MMD remains bounded away from zero is unstable under an unweighted gradient flow over the particle locations....
-
08
Text-Informed Training Data Filtering for Enhanced Virtual Flow Meter Performance
Kristoffer Hjelmen Nesland, Bjarne Grimstad, Antorweep Chakravorty, Dan Sui
stat.ML · cs.LG
In sectors such as energy, aquaculture and chemical processing, the effectiveness of both mechanistic and data-driven models is frequently limited by poor-quality training data, which obscures underlying physical laws and degrades predictive accuracy. Such quality issues commonly manifest as anomalies in the dataset, ranging from sensor faults to process upsets and incorrect operator inputs. While traditional rule-based filtering can remove a...
This edition is part of The Daily Abstract — stat.ML archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.