Statistical Learning
FAST opic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic Model Xiaobao Wu1 Thong Nguyen
Topic models have been evolving rapidly over the years, from conventional to recent neural models.
Leveraging an ECG Beat Diffusion Model for Morphological Reconstruction from Indirect Signals
Electrocardiogram (ECG) signals provide essential information about the heart's
Small coresets via negative dependence: DPPs, linear statistics, and concentration
Because sampling is tractable, DPPs are natural candidates for subsampling tasks, such as minibatch selection or coreset construction.
Information-Theoretic Generalization Analysis for Expected Calibration Error
While the expected calibration error (ECE), which employs binning, is widely adopted to evaluate the calibration performance of machine learning models, theoretical understanding of its estimation bias is limited. In this paper, we present the first comprehensive analysis of the estimation bias in the two common binning strategies, uniform mass and uniform width binning . Our analysis establishes upper bounds on the bias, achieving an improved convergence rate. Moreover, our bounds reveal, for the first time, the optimal number of bins to minimize the estimation bias. We further extend our bias analysis to generalization error analysis based on the information-theoretic approach, deriving upper bounds that enable the numerical evaluation of how small the ECE is for unknown data. Experiments using deep learning models show that our bounds are nonvacuous thanks to this information-theoretic generalization analysis approach.
Dissect Black Box: Interpreting for Rule-Based Explanations in Unsupervised Anomaly Detection Yu Zhang, Ruoyu Li, Nengwu Wu, Qing Li, Xinhan Lin, Y ang Hu, Tao Li, Yong Jiang
Delineation (GBD) algorithm is employed to define boundaries within each segmented distribution, effectively delineating normal from anomalous data points.
On the Stability and Generalization of Meta-Learning
We focus on developing a theoretical understanding of meta-learning. Given multiple tasks drawn i.i.d.
MALL T
Among all the contributing factors, the quality and selection of data is becoming increasingly recognized for its importance in training LLMs effectively.
TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks
While tabular classification has traditionally relied on from-scratch training, a recent breakthrough called prior-data fitted networks (PFNs) challenges this approach. Similar to large language models, PFNs make use of pretraining and in-context learning to achieve strong performance on new tasks in a single forward pass.
Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory
An adversary may be able to "steal" the model by querying for counterfactuals and training a
