{"total":35,"rows":[{"id":"2210.02410","title":"The Vendi Score: A Diversity Evaluation Metric for Machine Learning","created":"2022-10-05","cited_by_count":311,"area":null},{"id":"2502.02013","title":"Layer by Layer: Uncovering Hidden Representations in Language Models","created":"2025-02-04","cited_by_count":311,"area":null},{"id":"2405.20003","title":"Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities","created":"2024-05-30","cited_by_count":159,"area":null},{"id":"2412.09563","title":"Does Representation Matter? Exploring Intermediate Layers in Large Language Models","created":"2024-12-12","cited_by_count":34,"area":null},{"id":"2305.17326","title":"Matrix Information Theory for Self-Supervised Learning","created":"2023-05-27","cited_by_count":21,"area":null},{"id":"2309.17281","title":"Information Flow in Self-Supervised Learning","created":"2023-09-29","cited_by_count":16,"area":null},{"id":"2311.06597","title":"Understanding Grokking Through A Robustness Viewpoint","created":"2023-11-11","cited_by_count":12,"area":null},{"id":"2303.03237","title":"Convergence Rates for Non-Log-Concave Sampling and Log-Partition Estimation","created":"2023-03-06","cited_by_count":10,"area":null},{"id":"2305.16446","title":"The Representation Jensen-Shannon Divergence","created":"2023-05-25","cited_by_count":9,"area":null},{"id":"2206.13285","title":"Sum-of-Squares Relaxations for Information Theory and Variational Inference","created":"2022-06-27","cited_by_count":6,"area":null},{"id":"2402.03471","title":"The Information of Large Language Model Geometry","created":"2024-02-01","cited_by_count":5,"area":null},{"id":"2510.13025","title":"Information Shapes Koopman Representation","created":"2025-10-14","cited_by_count":4,"area":null},{"id":"2205.13941","title":"Auditing Differential Privacy in High Dimensions with the Kernel Quantum R\\'enyi Divergence","created":"2022-05-27","cited_by_count":3,"area":null},{"id":"2402.16481","title":"A kernel-based analysis of Laplacian Eigenmaps","created":"2024-02-26","cited_by_count":3,"area":null},{"id":"2406.03999","title":"Unveiling the Dynamics of Information Interplay in Supervised Learning","created":"2024-06-06","cited_by_count":3,"area":null},{"id":"2408.00549","title":"Learning to Embed Distributions via Maximum Kernel Entropy","created":"2024-08-01","cited_by_count":3,"area":null},{"id":"2408.16543","title":"Statistical and Geometrical properties of regularized Kernel Kullback-Leibler divergence","created":"2024-08-29","cited_by_count":3,"area":null},{"id":"2602.02117","title":"The Maximum von Neumann Entropy Principle: Theory and Applications in Machine Learning","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2305.07408","title":"Distributed Gradient Descent for Functional Learning","created":"2023-05-12","cited_by_count":2,"area":null},{"id":"2406.01435","title":"Learning Analysis of Kernel Ridgeless Regression with Asymmetric Kernel Learning","created":"2024-06-03","cited_by_count":2,"area":null},{"id":"2410.17998","title":"Estimating the Spectral Moments of the Kernel Integral Operator from Finite Sample Matrices","created":"2024-10-23","cited_by_count":2,"area":null},{"id":"2505.04613","title":"Kernel Embeddings and the Separation of Measure Phenomenon","created":"2025-05-07","cited_by_count":2,"area":null},{"id":"2602.14682","title":"Exposing Diversity Bias in Deep Generative Models: Statistical Origins and Correction of Diversity Error","created":"2026-02-16","cited_by_count":2,"area":null},{"id":"2310.05236","title":"Enhancing Kernel Flexibility via Learning Asymmetric Locally-Adaptive Kernels","created":"2023-10-08","cited_by_count":1,"area":null},{"id":"2409.16767","title":"Exploring Information-Theoretic Metrics Associated with Neural Collapse in Supervised Training","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2507.17582","title":"Physics-informed, boundary-constrained Gaussian process regression for the reconstruction of fluid flow fields","created":"2025-07-23","cited_by_count":1,"area":null},{"id":"2508.07982","title":"Likelihood Ratio Tests by Kernel Gaussian Embedding","created":"2025-08-11","cited_by_count":1,"area":null},{"id":"2410.14615","title":"Asymptotically Optimal Change Detection for Unnormalized Pre- and Post-Change Distributions","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2410.16195","title":"A Trust-Region Method for Graphical Stein Variational Inference","created":"2024-10-21","cited_by_count":0,"area":null},{"id":"2411.03759","title":"Variational Inference on the Boolean Hypercube with the Quantum Entropy","created":"2024-11-06","cited_by_count":0,"area":null},{"id":"2502.20763","title":"Information-Theoretic Perspectives on Optimizers","created":"2025-02-28","cited_by_count":0,"area":null},{"id":"2505.20433","title":"Kernel Quantile Embeddings and Associated Probability Metrics","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2507.06055","title":"Kernel Trace Distance: Quantum Statistical Metric between Measures through RKHS Density Operators","created":"2025-07-08","cited_by_count":0,"area":null},{"id":"2601.12375","title":"LiQSS: Post-Transformer Linear Quantum-Inspired State-Space Tensor Networks for Real-Time 6G","created":"2026-01-18","cited_by_count":0,"area":null},{"id":"2602.18364","title":"Quantum Maximum Likelihood Prediction via Hilbert Space Embeddings","created":"2026-02-20","cited_by_count":0,"area":null}],"next_cursor":null}