stat.ML · 2026-10-12 · No. 141
Machine Learning, 2026-10-12.
13 new papers in stat.ML. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
13 entries-
01
Hitting-Time Bounds for Asynchronous Q-Learning
Yang Peng
stat.ML · cs.LG
We study the last iterate of standard asynchronous Q-learning from a single trajectory of a finite Markov decision process. The trajectory follows a fixed behavior policy whose state--action chain is irreducible and may be periodic. For discount factor $γ$, write $H=(1-γ)^{-1}$, and let $μ_{\min}$ be the minimum stationary state--action probability and $\mathfrak h_\star$ the largest expected hitting time of the reverse state--action chain....
-
02
Finite-Sample Guarantees for Fully Discrete Conditional Diffusion Models
Qiuyun Zhu
stat.ML · cs.LG
We establish finite-sample guarantees for conditional diffusion models learned from data and implemented with finitely many denoising steps. Our approach aligns the score-training objective with the sampling grid, allowing statistical estimation and numerical discretization errors to be analyzed together. Under a smooth conditional density model, we derive high-probability bounds on the generated distribution's error and quantify the required...
-
03
Constrained Probabilistic Numerics: Gaussian Process Solvers for Linear PDEs under Linear Inequality Constraints
Boyuan Deng, Kshitiz Upadhyay, Michael Shields
stat.ML · cs.LG · math.NA
Gaussian process solvers for linear partial differential equations (PDEs) return posteriors rather than point estimates, but they condition only on equality information: the PDE residual, boundary data, and measurements. Many solutions of interest also obey inequality constraints, including nonnegativity, monotonicity, and absence of arbitrage, which equality conditioning cannot enforce. We prove that conditioning a Gaussian process prior...
-
04
From Pixels to Privacy-Sensitive Features: An Information-Theoretic Framework for Reconstruction Bounds
Henry Bourne, Robert F. Allison
stat.ML · cs.LG
What can an adversary recover from a model trained with DP-SGD? Its $(\varepsilon,δ)$ guarantee does not answer this question directly. We derive a distortion bound that can be computed before training and applies even to an adversary who observes the parameter trajectory during training, knows every other training record and the population distribution from which the training records are drawn. The analyst may choose the representation in...
-
05
How Well Do Prior-Data Fitted Networks Amortize Bayesian Inference?
Manuel Hülskamp, Julius Kobialka, Emanuel Sommer, Thomas Nagler, David Rügamer
stat.ML · cs.LG
Prior-data fitted networks (PFNs) are trained to approximate the Bayesian posterior predictive distribution (PPD) of a synthetic prior, yet results about the approximation quality are surprisingly thin. Taking an empirical risk minimization perspective, we decompose the deployment error of PFNs into prior, context, and amortization error, and measure the latter against a reference PPD under a realistic prior. Results show that PFNs generally...
-
06
Not All Dimensions Are Equal: Outlier-Aware Attention Linearization with Grouped Quadratic Kernels
Weiqi Sun, Qianyue Wu, Wenjia Wang, Tianyang Hu
stat.ML · cs.AI · cs.LG
Linearizing softmax attention offers a route to efficient Transformer inference, but preserving pretrained attention remains challenging. We identify an important source of approximation error overlooked by standard linearization methods: a small number of outlier dimensions contribute disproportionately to query-key dot products and account for a large fraction of the approximation error. Motivated by this heterogeneity, we propose...
-
07
Scalable Sparse Autoregressive Variational Inference for Non-Gaussian Spatial Fields
Paul F. V. Wiemann, Matthias Katzfuss
stat.ML · cs.LG · stat.CO · stat.ME
Latent field models are essential for spatial statistics, but the posterior distribution of the latent field, even with a Gaussian process (GP) prior, is analytically intractable whenever the likelihood is non-Gaussian. Existing approximations are either too slow or too restrictive for large non-Gaussian datasets. We present a scalable variational inference framework that mirrors the sparse nearest-neighbor autoregressive structure of the...
-
08
A Critical Look at Power Sampling when Test Time Sharpening LLMs
Abiel Malkani Talwar, Christopher Nemeth, Henry Moss
stat.ML · cs.LG
Reinforcement learning with verifiable rewards (RLVR) has substantially improved LLM reasoning, yet growing evidence suggests it mainly performs distribution sharpening: concentrating probability mass on reasoning paths the base model already produces. Recent work therefore seeks RLVR's gains without needing reward signals, by sampling from the power distribution $π_α\propto π_{\text{base}}^α$ via Markov chain Monte Carlo or sequential Monte...
-
09
Some remarks on the connection between generative diffusion and optimal transport
Giulio Biroli, Marc Mézard
stat.ML · cond-mat.dis-nn · cs.LG
We discuss three simple connections between generative diffusion and optimal transport. First, the joint law of the data and of their Ornstein-Uhlenbeck noising is, at every time, the solution of an entropic optimal-transport problem, at a temperature set by the noise level. Backward diffusion can consequently be read as an annealing which gradually decreases the entropic regularization. Second, we study the speciation transition--how the...
-
10
CorrFlow: Exact and Permutation-Equivariant Flow Matching on the Correlation Elliptope
Gautier Marti
stat.ML · cs.LG · q-fin.RM
Correlation matrices combine nonlinear positive-definiteness constraints with a simultaneous row-column permutation symmetry. Their generation therefore involves two distinct problems. First, every output must remain on the correlation elliptope, irrespective of how its variables are ordered. Second, the generator must learn the domain-specific distribution occupied by empirical data inside that valid space. Existing financial image...
-
11
Defence against the dark arts of distillation: Unsupervised discovery of subliminal learning
Joseph Egan, Ciarán M. Gilligan-Lee, Michael O'Riordan, Yuchen Zhu
stat.ML · cs.AI · cs.LG
When a language model is distilled from a teacher that shares its base parameters, the student can inherit behavioural traits of the teacher---including misalignment---even from data that is semantically unrelated to the trait (Cloud et al., 2026). All existing defences require knowing the trait. We remove this requirement and prove that a subliminally transferred trait can be recovered from the parameter updates alone, without supervision,...
-
12
Learning by Compression: Risk Estimates Attain the Law-of-Large-Numbers Rate
Simone Garatti, Marco C. Campi
stat.ML · cs.LG · math.ST
Compression schemes provide a general framework for deriving data-dependent risk bounds for learning algorithms. For learning rules based on preferent compression, existing results upper-bound the risk in terms of a sample-dependent complexity $\boldsymbol{k}$, defined as the cardinality of the compression augmented by the training examples on which the reconstructed hypothesis is inappropriate. These results, however, yield a margin of order...
-
13
Model-free Bayesian Clustering and Multimodal Posterior Summarisation
Qing Li, Sara Wade
stat.ML · cs.LG
We develop a model-free, noise-aware Bayesian clustering framework that constructs a martingale posterior over clusterings from a predictive Bayesian perspective. This avoids explicit likelihood-prior model specification, expensive MCMC sampling, and mode-seeking variational approximations, while accommodating irregular cluster shapes and enabling parallel generation of posterior draws. To interpret the posterior over high-dimensional,...
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.