{"total":51,"rows":[{"id":"2302.00401","title":"Deterministic equivalent and error universality of deep random features learning","created":"2023-02-01","cited_by_count":35,"area":null},{"id":"2308.09663","title":"GiGaMAE: Generalizable Graph Masked Autoencoder via Collaborative Latent Space Reconstruction","created":"2023-08-18","cited_by_count":21,"area":null},{"id":"2305.08013","title":"Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression","created":"2023-05-13","cited_by_count":19,"area":null},{"id":"2210.12760","title":"On double-descent in uncertainty quantification in overparametrized models","created":"2022-10-23","cited_by_count":16,"area":null},{"id":"2106.12912","title":"Information Bottleneck: Exact Analysis of (Quantized) Neural Networks","created":"2021-06-24","cited_by_count":15,"area":null},{"id":"2107.06898","title":"Towards quantifying information flows: relative entropy in deep neural networks and the renormalization group","created":"2021-07-14","cited_by_count":14,"area":null},{"id":"2103.05524","title":"On the interplay between data structure and loss function in classification problems","created":"2021-03-09","cited_by_count":13,"area":null},{"id":"2307.05635","title":"Fundamental limits of overparametrized shallow neural networks for supervised learning","created":"2023-07-11","cited_by_count":13,"area":null},{"id":"2402.13999","title":"Asymptotics of Learning with Deep Structured (Random) Features","created":"2024-02-21","cited_by_count":13,"area":null},{"id":"2110.14583","title":"Deep learning via message passing algorithms based on belief propagation","created":"2021-10-27","cited_by_count":12,"area":null},{"id":"2409.13904","title":"High-dimensional learning of narrow neural networks","created":"2024-09-20","cited_by_count":12,"area":null},{"id":"2105.03705","title":"Understanding Neural Networks with Logarithm Determinant Entropy Estimator","created":"2021-05-08","cited_by_count":10,"area":null},{"id":"2509.04492","title":"Learned Hallucination Detection in Black-Box LLMs using Token-level Entropy Production Rate","created":"2025-09-01","cited_by_count":10,"area":null},{"id":"2205.10009","title":"The price of ignorance: how much does it cost to forget noise structure in low-rank matrix estimation?","created":"2022-05-20","cited_by_count":9,"area":null},{"id":"2208.07951","title":"On the generalization of learning algorithms that do not converge","created":"2022-08-16","cited_by_count":9,"area":null},{"id":"2201.08082","title":"Kernel Methods and Multi-layer Perceptrons Learn Linear Models in High Dimensions","created":"2022-01-20","cited_by_count":8,"area":null},{"id":"2405.12755","title":"Progress Measures for Grokking on Real-world Tasks","created":"2024-05-21","cited_by_count":8,"area":null},{"id":"2305.04712","title":"High-Dimensional Smoothed Entropy Estimation via Dimensionality Reduction","created":"2023-05-08","cited_by_count":7,"area":null},{"id":"2206.13034","title":"Monitoring Shortcut Learning using Mutual Information","created":"2022-06-27","cited_by_count":6,"area":null},{"id":"2309.04522","title":"Connecting NTK and NNGP: A Unified Theoretical Framework for Wide Neural Network Learning Dynamics","created":"2023-09-08","cited_by_count":6,"area":null},{"id":"2505.03577","title":"Information-theoretic reduction of deep neural networks to linear models in the overparametrized proportional regime","created":"2025-05-06","cited_by_count":6,"area":null},{"id":"2207.09408","title":"Bounding generalization error with input compression: An empirical study with infinite-width networks","created":"2022-07-19","cited_by_count":4,"area":null},{"id":"2303.09995","title":"Neural-prior stochastic block model","created":"2023-03-17","cited_by_count":4,"area":null},{"id":"2407.20724","title":"Exploring Loss Landscapes through the Lens of Spin Glass Theory","created":"2024-07-30","cited_by_count":4,"area":null},{"id":"2503.13145","title":"High-entropy Advantage in Neural Networks' Generalizability","created":"2025-03-17","cited_by_count":4,"area":null},{"id":"2106.09021","title":"On the training of sparse and dense deep neural networks: less parameters, same performance","created":"2021-06-17","cited_by_count":3,"area":null},{"id":"2210.01237","title":"Bayes-optimal limits in structured PCA, and how to reach them","created":"2022-10-03","cited_by_count":3,"area":null},{"id":"2212.01572","title":"Approximate Message Passing for Multi-Layer Estimation in Rotationally Invariant Models","created":"2022-12-03","cited_by_count":3,"area":null},{"id":"2308.14938","title":"Entropy-based Guidance of Deep Neural Networks for Accelerated Convergence and Improved Performance","created":"2023-08-28","cited_by_count":3,"area":null},{"id":"2410.10200","title":"Fed-pilot: Optimizing LoRA Allocation for Efficient Federated Fine-Tuning with Heterogeneous Clients","created":"2024-10-14","cited_by_count":3,"area":null},{"id":"2110.12648","title":"Review-Based Domain Disentanglement without Duplicate Users or Contexts for Cross-Domain Recommendation","created":"2021-10-25","cited_by_count":2,"area":null},{"id":"2509.23695","title":"Estimating Time Series Foundation Model Transferability via In-Context Learning","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2510.22767","title":"TELL-TALE: Task Efficient LLMs with Task Aware Layer Elimination","created":"2025-10-26","cited_by_count":2,"area":null},{"id":"2511.13290","title":"Dropouts in Confidence: Moral Uncertainty in Human-LLM Alignment","created":"2025-11-17","cited_by_count":2,"area":"alignment"},{"id":"2603.03725","title":"Why Do Unlearnable Examples Work: A Novel Perspective of Mutual Information","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2206.04349","title":"Deep radiomic signature with immune cell markers predicts the survival of glioma patients","created":"2022-06-09","cited_by_count":1,"area":null},{"id":"2404.01364","title":"Information Plane Analysis Visualization in Deep Learning via Transfer Entropy","created":"2024-04-01","cited_by_count":1,"area":null},{"id":"2405.01584","title":"Lightweight Conceptual Dictionary Learning for Text Classification Using Information Compression","created":"2024-04-28","cited_by_count":1,"area":null},{"id":"2502.01472","title":"FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model","created":"2025-02-03","cited_by_count":1,"area":"alignment"},{"id":"2504.11781","title":"ACMamba: Fast Unsupervised Anomaly Detection via An Asymmetrical Consensus State Space Model","created":"2025-04-16","cited_by_count":1,"area":null},{"id":"2505.23790","title":"Rethinking the Understanding Ability across LLMs through Mutual Information","created":"2025-05-25","cited_by_count":1,"area":"lr"},{"id":"2508.07397","title":"A Spin Glass Characterization of Neural Networks","created":"2025-08-10","cited_by_count":1,"area":null},{"id":"2510.25262","title":"IBNorm: Information-Bottleneck Inspired Normalization for Representation Learning","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2206.08526","title":"k-Sliced Mutual Information: A Quantitative Study of Scalability with Dimension","created":"2022-06-17","cited_by_count":0,"area":null},{"id":"2302.07419","title":"Spatially heterogeneous learning by a deep student machine","created":"2023-02-15","cited_by_count":0,"area":null},{"id":"2306.06731","title":"An information-Theoretic Approach to Semi-supervised Transfer Learning","created":"2023-06-11","cited_by_count":0,"area":null},{"id":"2409.09262","title":"Informative Subgraphs Aware Masked Auto-Encoder in Dynamic Graphs","created":"2024-09-14","cited_by_count":0,"area":null},{"id":"2510.20284","title":"Knowledge-Informed Neural Network for Complex-Valued SAR Image Recognition","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2605.14738","title":"TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2607.11541","title":"Random Label Prediction Heads for Studying Memorization in Deep Neural Networks","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2610.14290","title":"Layer-wise Input Recoverability in Deep Neural Networks","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}