Statistical Learning

Generalization Guarantees for Representation Learning via Data-Dependent Gaussian Mixture Priors ICLR 2025 Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis ICLR 2025 Generalization through variance: how noise shapes inductive biases in diffusion models ICLR 2025 Generalized multi-view model: Adaptive density estimation under low-rank constraints JMLR 2025 GHOST: Gaussian Hypothesis Open-Set Technique AAAI 2025 Graph-accelerated Markov Chain Monte Carlo using Approximate Samples JMLR 2025 Guaranteed Prediction Sets for Functional Surrogate Models UAI 2025 Heterogeneous Sufficient Dimension Reduction and Subspace Clustering ICML 2025 High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws ICLR 2025 High-Dimensional Differential Parameter Inference in Exponential Family using Time Score Matching AISTATS 2025 How good is your Laplace approximation of the Bayesian posterior? Finite-sample computable error bounds for a variety of useful divergences JMLR 2025 How many samples are needed to train a deep neural network? ICLR 2025 How Much is Unseen Depends Chiefly on Information About the Seen ICLR 2025 How to Verify Any (Reasonable) Distribution Property: Computationally Sound Argument Systems for Distributions ICLR 2025 Identifiability for Gaussian Processes with Holomorphic Kernels ICLR 2025 Identity Curvature Laplace Approximation for Improved Out-of-Distribution Detection WACV 2025 If Attention Serves as a Cognitive Model of Human Memory Retrieval, What is the Plausible Memory Representation? ACL 2025 Improved dependence on coherence in eigenvector and eigenvalue estimation error bounds AISTATS 2025 Improving the Statistical Efficiency of Cross-Conformal Prediction ICML 2025 In-Context Learning and Occam’s Razor ICML 2025 Independence Tests for Language Models ICML 2025 Inferring Change Points in High-Dimensional Regression via Approximate Message Passing JMLR 2025 InspectorRAGet: An Introspection Platform for RAG Evaluation NAACL 2025 Instability, Computational Efficiency and Statistical Accuracy JMLR 2025 Instance-level Randomization: Toward More Stable LLM Evaluations EMNLP 2025