{"list":"other","total":66,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"1912.02178","title":"Fantastic Generalization Measures and Where to Find Them","created":"2019-12-04","cited_by_count":513},{"id":"1412.6614","title":"In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning","created":"2014-12-20","cited_by_count":342},{"id":"2110.11216","title":"User-friendly introduction to PAC-Bayes bounds","created":"2021-10-21","cited_by_count":239},{"id":"2309.10668","title":"Language Modeling Is Compression","created":"2023-09-19","cited_by_count":225},{"id":"1902.04742","title":"Uniform convergence may be unable to explain generalization in deep learning","created":"2019-02-13","cited_by_count":224},{"id":"1905.08539","title":"Universal Approximation with Deep Narrow Networks","created":"2019-05-21","cited_by_count":200},{"id":"1805.08522","title":"Deep learning generalizes because the parameter-function map is biased towards simple functions","created":"2018-05-22","cited_by_count":183},{"id":"2002.10689","title":"A Theory of Usable Information Under Computational Constraints","created":"2020-02-25","cited_by_count":162},{"id":"1710.05468","title":"Generalization in Deep Learning","created":"2017-10-16","cited_by_count":146},{"id":"1511.02476","title":"Statistical physics of inference: Thresholds and algorithms","created":"2015-11-08","cited_by_count":128},{"id":"1804.05862","title":"Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach","created":"2018-04-16","cited_by_count":126},{"id":"1910.07833","title":"Sharper bounds for uniformly stable algorithms","created":"2019-10-17","cited_by_count":93},{"id":"1405.2420","title":"Optimal Learners for Multiclass Problems","created":"2014-05-10","cited_by_count":65},{"id":"2304.05366","title":"The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning","created":"2023-04-11","cited_by_count":63},{"id":"1806.05451","title":"The committee machine: Computational to statistical gaps in learning a two-layers neural network","created":"2018-06-14","cited_by_count":58},{"id":"2404.09937","title":"Compression Represents Intelligence Linearly","created":"2024-04-15","cited_by_count":56},{"id":"2503.02113","title":"Deep Learning is Not So Mysterious or Different","created":"2025-03-03","cited_by_count":56},{"id":"2312.17173","title":"Non-Vacuous Generalization Bounds for Large Language Models","created":"2023-12-28","cited_by_count":53},{"id":"2601.03220","title":"From Entropy to Epiplexity: Rethinking Information for Computationally Bounded Intelligence","created":"2026-01-06","cited_by_count":41},{"id":"1908.08484","title":"Minimum Description Length Revisited","created":"2019-08-21","cited_by_count":37},{"id":"2503.14337","title":"PENCIL: Long Thoughts with Short Memory","created":"2025-03-18","cited_by_count":33},{"id":"2401.14953","title":"Learning Universal Predictors","created":"2024-01-26","cited_by_count":31},{"id":"2304.06670","title":"Deep neural networks have an inbuilt Occam's razor","created":"2023-04-13","cited_by_count":28},{"id":"2407.18158","title":"Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models","created":"2024-07-25","cited_by_count":25},{"id":"2006.05942","title":"On Uniform Convergence and Low-Norm Interpolation Learning","created":"2020-06-10","cited_by_count":24},{"id":"2510.10981","title":"In-Context Learning Is Provably Bayesian Inference: A Generalization Theory for Meta-Learning","created":"2025-10-13","cited_by_count":22},{"id":"2309.13658","title":"Fantastic Generalization Measures are Nowhere to be Found","created":"2023-09-24","cited_by_count":19},{"id":"2506.12027","title":"Constant Bit-size Transformers Are Turing Complete","created":"2025-05-22","cited_by_count":19},{"id":"2402.06323","title":"How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers","created":"2024-02-09","cited_by_count":18},{"id":"1510.04931","title":"Bad Universal Priors and Notions of Optimality","created":"2015-10-16","cited_by_count":16},{"id":"2202.04513","title":"The no-free-lunch theorems of supervised learning","created":"2022-02-09","cited_by_count":16},{"id":"2006.08753","title":"Pessimism About Unknown Unknowns Inspires Conservatism","created":"2020-06-15","cited_by_count":13},{"id":"2103.04554","title":"Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models","created":"2021-03-08","cited_by_count":13},{"id":"2210.12082","title":"A Non-Asymptotic Moreau Envelope Theory for High-Dimensional Generalized Linear Models","created":"2022-10-21","cited_by_count":11},{"id":"2511.12659","title":"Sample Complexity of Agnostic Multiclass Classification: Natarajan Dimension Strikes Back","created":"2025-11-16","cited_by_count":9},{"id":"2511.22226","title":"Embedded Universal Predictive Intelligence: a coherent framework for multi-agent learning","created":"2025-11-27","cited_by_count":9},{"id":"2602.23643","title":"AI Must Embrace Specialization via Superhuman Adaptable Intelligence","created":"2026-02-27","cited_by_count":8},{"id":"2103.11956","title":"The Implications of the No-Free-Lunch Theorems for Meta-induction","created":"2021-03-22","cited_by_count":6},{"id":"2408.12065","title":"Transformers As Approximations of Solomonoff Induction","created":"2024-08-22","cited_by_count":6},{"id":"2509.22445","title":"Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers","created":"2025-09-26","cited_by_count":6},{"id":"1604.03343","title":"Loss Bounds and Time Complexity for Speed Priors","created":"2016-04-12","cited_by_count":5},{"id":"2409.09626","title":"Understanding Simplicity Bias towards Compositional Mappings via Learning Dynamics","created":"2024-09-15","cited_by_count":5},{"id":"2511.20888","title":"Deep Learning as a Convex Paradigm of Computation: Minimizing Circuit Size with ResNets","created":"2025-11-25","cited_by_count":5},{"id":"2005.04791","title":"Absolutely No Free Lunches!","created":"2020-05-10","cited_by_count":4},{"id":"2111.05321","title":"Turing-Universal Learners with Optimal Scaling Laws","created":"2021-11-09","cited_by_count":4},{"id":"2206.06473","title":"A Dilemma for Solomonoff Prediction","created":"2022-06-13","cited_by_count":4},{"id":"2502.08593","title":"Toward Universal Laws of Outlier Propagation","created":"2025-02-12","cited_by_count":3},{"id":"2512.17086","title":"Value Under Ignorance in Universal Artificial Intelligence","created":"2025-12-18","cited_by_count":3},{"id":"1507.04124","title":"On the Computability of Solomonoff Induction and Knowledge-Seeking","created":"2015-07-15","cited_by_count":2},{"id":"1707.08747","title":"A Formal Approach to the Problem of Logical Non-Omniscience","created":"2017-07-27","cited_by_count":2},{"id":"2503.02110","title":"Quantifying Overfitting along the Regularization Path for Two-Part-Code MDL in Supervised Classification","created":"2025-03-03","cited_by_count":2},{"id":"2603.20274","title":"Solomonoff induction","created":"2026-03-17","cited_by_count":2},{"id":"1501.00601","title":"Ultimate Intelligence Part I: Physical Completeness and Objectivity of Induction","created":"2015-01-03","cited_by_count":1},{"id":"2404.16050","title":"Implications of computer science theory for the simulation hypothesis","created":"2024-04-09","cited_by_count":1},{"id":"2509.12337","title":"Determination of the fifth Busy Beaver value","created":"2025-09-15","cited_by_count":1},{"id":"2604.13609","title":"Golden Handcuffs make safer AI agents","created":"2026-04-15","cited_by_count":1},{"id":"2606.04834","title":"Prediction Under Imperfect Compression: A Theory of Approximate MDL","created":"2026-06-03","cited_by_count":1},{"id":"2606.13576","title":"Learning with Simulators: No Regret in a Computationally Bounded World","created":"2026-06-11","cited_by_count":1},{"id":"2606.31282","title":"Revisiting the Volume Hypothesis","created":"2026-06-30","cited_by_count":1},{"id":"2609.30063","title":"Self-Play Pretraining with Zero Data","created":"2026-09-24","cited_by_count":1}],"next_cursor":null}