Statistics (Machine Learning) Papers@StatsPapersSep 17, 2024Automated by @PremiumAcctsA Survey on Statistical Theory of Deep Learning: Approximation, Training Dynamics, and Generative Models. arxiv.org/abs/2401.0718711515126326324K24K
Statistics (Machine Learning) Papers@StatsPapersJun 17, 2025Automated by @PremiumAcctsRandom Matrix Theory for Deep Learning: Beyond Eigenvalues of Linear Models. arxiv.orgRandom Matrix Theory for Deep Learning: Beyond Eigenvalues of Linear ModelsModern Machine Learning (ML) and Deep Neural Networks (DNNs) often operate on high-dimensional data and rely on overparameterized models, where classical low-dimensional intuitions break down. In...38381981987.9K7.9K
Statistics (Machine Learning) Papers@StatsPapersJul 18, 2019Automated by @PremiumAcctsPotential Outcome and Directed Acyclic Graph Approaches to Causality: Relevance for Empirical Practice in Economics. arxiv.org/abs/1907.072715555163163
Statistics (Machine Learning) Papers@StatsPapersJul 22, 2025Automated by @PremiumAcctsStatistical and Algorithmic Foundations of Reinforcement Learning. arxiv.org/abs/2507.1444435351711718.4K8.4K
Statistics (Machine Learning) Papers@StatsPapersMay 21, 2024Automated by @PremiumAcctsCan a Transformer Represent a Kalman Filter?. arxiv.orgCan a Transformer Represent a Kalman Filter?Transformers are a class of autoregressive deep learning architectures which have recently achieved state-of-the-art performance in various vision, language, and robotics tasks. We revisit the...22272713913917K17K
Statistics (Machine Learning) Papers@StatsPapersAug 19, 2025Automated by @PremiumAcctsUniversal Learning of Nonlinear Dynamics. arxiv.orgUniversal Learning of Nonlinear DynamicsWe study the fundamental problem of learning a marginally stable unknown nonlinear dynamical system. We describe an algorithm for this problem, based on the technique of spectral filtering, which...19191171175.7K5.7K
Statistics (Machine Learning) Papers@StatsPapersJun 26, 2019Automated by @PremiumAcctsMonte Carlo Gradient Estimation in Machine Learning. arxiv.org/abs/1906.106521919114114
Statistics (Machine Learning) Papers@StatsPapersMay 24, 2017Automated by @PremiumAcctsThe Marginal Value of Adaptive Gradient Methods in Machine Learning. arxiv.org/abs/1705.082924646106106
Statistics (Machine Learning) Papers@StatsPapersApr 26, 2025Automated by @PremiumAcctsLinear Convergence of Diffusion Models Under the Manifold Hypothesis. arxiv.org/abs/2410.0904611121296964.8K4.8K
Statistics (Machine Learning) Papers@StatsPapersJun 2, 2025Automated by @PremiumAcctsA Mathematical Perspective On Contrastive Learning. arxiv.orgA Mathematical Perspective On Contrastive LearningMultimodal contrastive learning is a methodology for linking different data modalities; the canonical example is linking image and text data. The methodology is typically framed as the...11101097974.1K4.1K
Statistics (Machine Learning) Papers@StatsPapersJun 3, 2025Automated by @PremiumAcctsRiemannian Principal Component Analysis. arxiv.org/abs/2506.00226151596964.4K4.4K
Statistics (Machine Learning) Papers@StatsPapersJul 22, 2025Automated by @PremiumAcctsDiffusion Models for Time Series Forecasting: A Survey. arxiv.org/abs/2507.14507242488883.5K3.5K
Statistics (Machine Learning) Papers@StatsPapersFeb 15, 2025Automated by @PremiumAcctsRegularization can make diffusion models more efficient. arxiv.org/abs/2502.0915111161686865.8K5.8K
Statistics (Machine Learning) Papers@StatsPapersJun 6, 2024Automated by @PremiumAcctsThe No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning. arxiv.orgThe No Free Lunch Theorem, Kolmogorov Complexity, and the Role of...No free lunch theorems for supervised learning state that no learner can solve all problems or that all learners achieve exactly the same accuracy on average over a uniform distribution on...161684848.4K8.4K