stat.ML · 2026-09-10 · No. 111
Machine Learning, 2026-09-10.
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
A statistical approach to bias in zero-shot learning: the lens of handwriting recognition
Clarence Chew, Gim Siang Chia, Sukalpa Chanda, Subhroshekhar Ghosh, Soumendu Sundar Mukherjee
stat.ML · cs.AI · cs.CV · cs.LG
Generalized zero-shot learning (GZSL) has emerged as an important paradigm for visual recognition systems that must generalize to classes that were not observed during training. Traditional GZSL techniques are limited by their applicability to a relatively small number of such unseen classes, scalability beyond which is challenging due to its well-known misclassification bias towards classes observed during training. In this work, we...
-
02
Optimal Value Inference for Reinforcement Learning
Nan Lu, Ethan Lee, James M. Robins, David Simchi-Levi, Junwei Lu
stat.ML · cs.LG · stat.ME
We study offline inference for the optimal value in reinforcement learning. Two new nuisances are derived as fixed points of a self-induced Bellman equation, in which we approximate the maximum Bellman operator by its softmax correspondence. We propose a debiased estimator through the Neyman orthogonality and establish its asymptotic normality under diverging horizons even when the behavior policy changes with time, as long as the nuisances...
-
03
FlowCPO: A Unified Divergence View of Preference Alignment for Flow Models
Yansen Han, Shengyi Liao, Peng Sun, Deyuan Liu, Yuanxing Zhang, Pengfei Wan, Tao Lin
stat.ML · cs.AI · cs.CV · cs.LG
Preference alignment for flow and diffusion models now spans online reinforcement learning and offline preference optimization, but the relation between these methods remains unclear. In particular, existing forward-process alignment methods require fresh samples from the current model, while offline methods based on fixed preference pairs rely primarily on positive-only fine-tuning or DPO-style likelihood-ratio surrogates. We organize these...
-
04
A Unifying Perspective on Probabilities as Model Predictions
Benedikt Höltgen
stat.ML · cs.CY · cs.LG · math.ST
Although probabilistic statements are ubiquitous, foundational disagreements persist about their understanding, as exemplified by debates between Bayesians and frequentists; moreover, it is unclear when and why acting on them actually leads to desirable outcomes. Here, we argue that every probability is the output of a \emph{prediction method}, that is, it depends on both a particular way of constructing abstractions and a way of transforming...
-
05
Why Learning Rediscovers the Closed-Form Diagonal Regularizer
Jeahn Han, Pyojin Kim
stat.ML · cs.LG · cs.RO · eess.AS
We identify a diagonal saturation principle in modal inverse problems: when truncation noise is isotropic, the Bayes-optimal Tikhonov shape is a closed-form power law Gamma_k proportional to lambda_k^|s| set by the prior alone, independent of the domain. Berry's random-wave conjecture decorrelates the truncation noise across modes, and Weyl's eigenvalue counting law supplies enough modes for the conclusion to survive empirical Berry...
-
06
Distillation of Synthetic Data for Time Series Foundation Models
Niloy Biswas, Noureddine El Karoui
stat.ML · cs.LG
Time series foundation models (TSFMs) are increasingly pre-trained on synthetically generated time series trajectories, where the data generating process is known. Current pre-training recipes are based on loss objectives which compare TSFM outputs to realized future values of each trajectory. We instead propose loss objectives which compare TSFM outputs to the conditional forecast distribution of each trajectory, a procedure we call...
-
07
Learning with Synthetic Data via SGD in High-Dimensional Linear Regression
Jichu li, Difan Zou
stat.ML · cs.AI · cs.LG
Synthetic data has become a promising way to scale model training beyond limited human-generated data but it may also induce strong model collapse (Dohmatob et al., 2024), where any fixed fraction of synthetic data prevents model performance from improving under data scaling, leaving a non-vanishing excess risk floor. In this paper, we study how synthetic data affects the generalization of one-pass SGD in high-dimensional linear regression...
-
08
High-probability guarantees for linear accessibility in feature superposition
Enrico Vompa
stat.ML · cs.AI · cs.IR · cs.LG · math.PR
Neural networks can leverage feature superposition to encode more concepts than dimensions, but cross-feature interference constrains the linear accessibility of simultaneously active features. By framing linear accessibility as a compressed sensing problem, we derive high-probability bounds for fixed supports under subgaussian noise, proving the sufficient dimension scales linearly ($d=O_{\varepsilon}(k \log m)$) rather than prior worst-case...
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.