{"total":17,"rows":[{"id":"2503.02113","title":"Deep Learning is Not So Mysterious or Different","created":"2025-03-03","cited_by_count":56,"area":null},{"id":"2410.02724","title":"Large Language Models as Markov Chains","created":"2024-10-03","cited_by_count":35,"area":null},{"id":"2410.18779","title":"A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2501.19067","title":"From Low Intrinsic Dimensionality to Non-Vacuous Generalization Bounds in Deep Multi-Task Learning","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2504.15208","title":"Compute-Optimal LLMs Provably Generalize Better With Scale","created":"2025-04-21","cited_by_count":5,"area":null},{"id":"2602.06181","title":"Investigating Social Bias Changes in Quantized Language Models","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2409.17932","title":"Sample Compression Unleashed: New Generalization Bounds for Real Valued Losses","created":"2024-09-26","cited_by_count":4,"area":null},{"id":"2410.13577","title":"Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks","created":"2024-10-17","cited_by_count":3,"area":null},{"id":"2503.07325","title":"Non-vacuous Generalization Bounds for Deep Neural Networks without any modification to the trained models","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2505.15496","title":"Fast Rate Bounds for Multi-Task and Meta-Learning with Different Sample Sizes","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2602.23128","title":"Bound to Disagree: Generalization Bounds via Certifiable Surrogates","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2602.01126","title":"WinFLoRA: Incentivizing Client-Adaptive Aggregation in Federated LoRA under Privacy Heterogeneity","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2509.07963","title":"Customizing the Inductive Biases of Softmax Attention using Structured Matrices","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2602.16065","title":"Can Generative Artificial Intelligence Survive Data Contamination? Theoretical Guarantees under Contaminated Recursive Training","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2609.32271","title":"Certification Frontiers for Gaussian LoRA: Independent Priors, Posterior Risk, and Prediction-Preserving Balancing","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.34458","title":"Understanding Generalization Requires Universal Induction","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.34731","title":"Information-Theoretic Analysis of Next-Token Prediction under Markovian Data","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}