{"total":15,"rows":[{"id":"2106.03970","title":"Batch Normalization Orthogonalizes Representations in Deep Random Networks","created":"2021-06-07","cited_by_count":29,"area":null},{"id":"2202.05258","title":"Hardness of Noise-Free Learning for Two-Hidden-Layer Neural Networks","created":"2022-02-10","cited_by_count":28,"area":null},{"id":"2101.08303","title":"From Local Pseudorandom Generators to Hardness of Learning","created":"2021-01-20","cited_by_count":24,"area":null},{"id":"2201.06699","title":"AESPA: Accuracy Preserving Low-degree Polynomial Activation for Fast Private Inference","created":"2022-01-18","cited_by_count":14,"area":null},{"id":"2205.16003","title":"Learning (Very) Simple Generative Models Is Hard","created":"2022-05-31","cited_by_count":9,"area":null},{"id":"2305.05765","title":"On the average-case complexity of learning output distributions of quantum circuits","created":"2023-05-09","cited_by_count":9,"area":null},{"id":"2510.00345","title":"Cutting the Skip: Training Residual-Free Transformers","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2107.09200","title":"A quantum algorithm for training wide and deep classical neural networks","created":"2021-07-19","cited_by_count":7,"area":null},{"id":"2505.20802","title":"Leaner Transformers: More Heads, Less Depth","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2105.00507","title":"Universal scaling laws in the gradient descent training of neural networks","created":"2021-05-02","cited_by_count":4,"area":null},{"id":"2507.15290","title":"Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown","created":"2025-07-21","cited_by_count":4,"area":null},{"id":"2505.12789","title":"Enhancing Transformers Through Conditioned Embedded Tokens","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2603.07162","title":"Spectral Conditioning of Attention Improves Transformer Performance","created":"2026-03-07","cited_by_count":3,"area":null},{"id":"2305.16508","title":"Most Neural Networks Are Almost Learnable","created":"2023-05-25","cited_by_count":2,"area":null},{"id":"2609.07086","title":"Conditioned Initialization for Attention","created":"2026-09-07","cited_by_count":0,"area":null}],"next_cursor":null}