{"total":38,"rows":[{"id":"2107.01163","title":"Unveiling the structure of wide flat minima in neural networks","created":"2021-07-02","cited_by_count":28,"area":null},{"id":"2202.03038","title":"Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry","created":"2022-02-07","cited_by_count":28,"area":null},{"id":"2110.00683","title":"Learning through atypical \"phase transitions\" in overparameterized neural networks","created":"2021-10-01","cited_by_count":21,"area":null},{"id":"2102.13069","title":"Proof of the Contiguity Conjecture and Lognormal Limit for the Symmetric Perceptron","created":"2021-02-25","cited_by_count":18,"area":null},{"id":"2111.03084","title":"Binary perceptron: efficient algorithms can find solutions in a rare well-connected cluster","created":"2021-11-04","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":"2309.10688","title":"On the different regimes of Stochastic Gradient Descent","created":"2023-09-19","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":"2310.12802","title":"An effective theory of collective deep learning","created":"2023-10-19","cited_by_count":7,"area":null},{"id":"2306.11232","title":"Eight challenges in developing theory of intelligence","created":"2023-06-20","cited_by_count":6,"area":null},{"id":"2310.05401","title":"Entropy-MCMC: Sampling from Flat Basins with Ease","created":"2023-10-09","cited_by_count":6,"area":null},{"id":"2202.00339","title":"Quantifying Relevance in Learning and Inference","created":"2022-02-01","cited_by_count":5,"area":null},{"id":"2305.17332","title":"Learning Capacity: A Measure of the Effective Dimensionality of a Model","created":"2023-05-27","cited_by_count":4,"area":null},{"id":"2309.09240","title":"High-dimensional manifold of solutions in neural networks: insights from statistical physics","created":"2023-09-17","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":"2104.05600","title":"PAC Bayesian Performance Guarantees for Deep (Stochastic) Networks in Medical Imaging","created":"2021-04-12","cited_by_count":3,"area":null},{"id":"2112.01433","title":"Loss Landscape Dependent Self-Adjusting Learning Rates in Decentralized Stochastic Gradient Descent","created":"2021-12-02","cited_by_count":3,"area":null},{"id":"2112.10219","title":"Quantum Approximate Optimization Algorithm applied to the binary perceptron","created":"2021-12-19","cited_by_count":3,"area":null},{"id":"2410.18858","title":"Bilinear Sequence Regression: A Model for Learning from Long Sequences of High-dimensional Tokens","created":"2024-10-24","cited_by_count":3,"area":null},{"id":"2507.04448","title":"Transfer Learning in Infinite Width Feature Learning Networks","created":"2025-07-06","cited_by_count":3,"area":null},{"id":"2606.06533","title":"Position: Don't Just \"Fix it in Post\": A Science of AI Must Study Training Dynamics","created":"2026-06-03","cited_by_count":3,"area":null},{"id":"2505.02296","title":"Entropy-Guided Sampling of Flat Modes in Discrete Spaces","created":"2025-05-05","cited_by_count":2,"area":null},{"id":"2111.13302","title":"Equivalence between algorithmic instability and transition to replica symmetry breaking in perceptron learning systems","created":"2021-11-26","cited_by_count":1,"area":null},{"id":"2303.07874","title":"Bayes Complexity of Learners vs Overfitting","created":"2023-03-13","cited_by_count":1,"area":null},{"id":"2406.15664","title":"Flat Posterior Does Matter For Bayesian Model Averaging","created":"2024-06-21","cited_by_count":1,"area":null},{"id":"2501.02436","title":"Network Dynamics-Based Framework for Understanding Deep Neural Networks","created":"2025-01-05","cited_by_count":1,"area":null},{"id":"2502.16292","title":"Generative diffusion for perceptron problems: statistical physics analysis and efficient algorithms","created":"2025-02-22","cited_by_count":1,"area":null},{"id":"2603.15367","title":"Controlled Langevin Dynamics for Sampling of Feedforward Neural Networks Trained with Minibatches","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2107.07757","title":"Entropic alternatives to initialization","created":"2021-07-16","cited_by_count":0,"area":null},{"id":"2210.04745","title":"Low-power multi-mode fiber projector overcomes shallow neural networks classifiers","created":"2022-10-10","cited_by_count":0,"area":null},{"id":"2309.06774","title":"Fundamental Limits of Deep Learning-Based Binary Classifiers Trained with Hinge Loss","created":"2023-09-13","cited_by_count":0,"area":null},{"id":"2402.05025","title":"Strong convexity-guided hyper-parameter optimization for flatter losses","created":"2024-02-07","cited_by_count":0,"area":null},{"id":"2504.16136","title":"Active Learning Methods for Efficient Data Utilization and Model Performance Enhancement","created":"2025-04-21","cited_by_count":0,"area":null},{"id":"2602.06837","title":"Sharpness-Aware Hybrid Model Learning for Architecture-Agnostic Parameter Estimation","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2603.29529","title":"Sampling at intermediate temperatures is optimal for training large language models in protein structure prediction","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2605.09256","title":"Improving Generalization by Permutation Routing Across Model Copies","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2607.28428","title":"Kohn-Sham Spectral Embedding on Sparse Graphs at the Nishimori Temperature for Image Classification","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2609.09589","title":"A Function-Space Approach to the Statistical Mechanics of Learning Dynamics","created":"2026-09-09","cited_by_count":0,"area":null}],"next_cursor":null}