1. Saddle-to-Saddle Dynamics Explains A Simplicity Bias Across Neural Network Architectures
   2025/12/23 by Yedi Zhang, Andrew Saxe, Zhang, Yedi +3 · 2 voices · 3 citations
   Computer Science · #Artificial neural network #Class (philosophy) #Convolutional neural network #Domain Adaptation and Few-Shot Learning #Generative Adversarial Networks and Image Synthesis #Gradient descent #Initialization #Invariant (physics) #Simplicity #Stochastic Gradient Optimization Techniques
2. Structure-Preserving Physics-Informed Neural Network for the Korteweg--de Vries (KdV) Equation
   2025/11/01 by Victory Obieke, Emmanuel Oguadimma, Obieke, Victory +1 · 3 citations
   Computer Science · Mathematics · Physics and Astronomy · #Artificial neural network #Backpropagation #Hamiltonian (control theory) #Initialization #Korteweg–de Vries equation #Model Reduction and Neural Networks #Neural Networks and Reservoir Computing #Nonlinear system #Ordinary differential equation #Partial differential equation #Quantum many-body systems #Regularization (linguistics) #cs.LG #math-ph #math.MP #nlin.PS #physics.flu-dyn
3. Language Models are Injective and Hence Invertible
   2025/10/17 by Giorgos Nikolaou, Nikolaou, Giorgos, Tommaso Mencattini +9 · 43 voices · 6 citations
   Computer Science · Medicine · #Artificial Intelligence in Healthcare and Education #Initialization #Injective function #Invertible matrix #Language model #Multimodal Machine Learning Applications #Property (philosophy) #Sequence (biology) #Topic Modeling #Transformer #cs.AI #cs.LG
4. No More Adam: Learning Rate Scaling at Initialization is All You Need
   2024/12/16 by Minghao Xu, Lichuan Xiang, Xu, Minghao +6 · 7 voices · 2 citations
   Computer Science · Mathematics · #Adam smith #Artificial intelligence #Computer science #Economics #Initialization #Mathematics #Neoclassical economics #Programming language #Scaling #Teaching and Learning Programming
5. Local Convergence of Approximate Newton Method for Two Layer Nonlinear Regression
   2023/11/26 by Zhihang Li, Zhao Song, Li, Zhihang +5 · 1 citation
   Computer Science · Mathematics · #Algorithm #Applied mathematics #Artificial intelligence #Artificial neural network #Computer science #Convergence (economics) #Economics #FOS: Computer and information sciences #Function (biology) #Hessian matrix #Initialization #Lipschitz continuity #Machine Learning (cs.LG) #Machine Learning and ELM #Mathematical analysis #Mathematical optimization #Mathematics #Matrix Theory and Algorithms #Regression #Softmax function #Statistics #Stochastic Gradient Optimization Techniques
6. Composable Function-preserving Expansions for Transformer Architectures
   2023/08/11 by Andréa Gesmundo, Andrea Gesmundo, Kaitlin Maile +2 · 1 voice · 2 citations
   Computer Science · Engineering · #Advanced Neural Network Applications #Architecture #Artificial intelligence #Artificial neural network #Computer science #Deep neural networks #Domain Adaptation and Few-Shot Learning #Engineering #Initialization #Neural Networks and Applications #Programming language #Scratch #Transformation (genetics) #Transformer #cs.LG
7. Are sketch-and-precondition least squares solvers numerically stable?
   2023/02/14 by Maike Meier, Yuji Nakatsukasa, Meier, Maike +5 · 4 citations
   Computer Science · Engineering · Mathematics · Physics and Astronomy · #Advanced Numerical Methods in Computational Mathematics #Algorithm #Applied mathematics #Combinatorics #Computer science #Electromagnetic Scattering and Analysis #FOS: Mathematics #Initialization #Iterative method #Iterative refinement #Mathematical optimization #Mathematics #Matrix (chemical analysis) #Matrix Theory and Algorithms #Numerical Analysis (math.NA) #Precondition #Preconditioner #Sketch #Solver
8. Learning Single-Index Models with Shallow Neural Networks
   2022/10/27 by Alberto Bietti, Joan Bruna, Bietti, Alberto +5 · 16 citations
   Computer Science · Mathematics · #Algorithm #Artificial intelligence #Artificial neural network #Class (philosophy) #Computer science #Dimension (graph theory) #Exploit #FOS: Computer and information sciences #FOS: Mathematics #Function (biology) #Generalization #Index (typography) #Initialization #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Machine learning #Mathematics #Multivariate statistics #Neural Networks and Applications #Optimization and Control (math.OC) #Sample (material) #Stochastic Gradient Optimization Techniques #Subspace topology #Univariate
9. DeepNet: Scaling Transformers to 1,000 Layers
   2022/03/01 by Hongyu Wang, Shuming Ma, Wang, Hongyu +10 · 2 voices · 29 citations
   Computer Science · Engineering · Mathematics · #Advanced Neural Network Applications #Algorithm #Artificial intelligence #Bounded function #Computer science #Electrical engineering #Engineering #Ferroelectric and Negative Capacitance Devices #Geometry #Initialization #Mathematical analysis #Mathematics #Neural Networks and Reservoir Computing #Normalization (sociology) #Residual #Scaling #Transformer #Voltage
10. Regularized Newton Method with Global O(1/k²) Convergence
    2021/12/03 by Konstantin Mishchenko, Mishchenko, Konstantin · 1 voice · 10 citations
    Computer Science · Mathematics · #Advanced Optimization Algorithms Research #Applied mathematics #Combinatorics #Computer science #Geometry #Initialization #Iterated function #Iterative Methods for Nonlinear Equations #Iterative method #Line search #Lipschitz continuity #Local convergence #Mathematical analysis #Mathematical optimization #Mathematics #Nabla symbol #Omega #Optimization and Variational Analysis #Physics #Rate of convergence #Regular polygon #Regularization (linguistics) #cs.LG #math.OC
11. Few-shot acoustic event detection via meta-learning
    2020/02/21 by Bowen Shi, Ming Sun, Shi, Bowen +9 · 2 citations
    Computer Science · Engineering · Mathematics · #Artificial intelligence #Artificial neural network #Audio and Speech Processing (eess.AS) #Computer science #Domain (mathematical analysis) #Engineering #Event (particle physics) #FOS: Computer and information sciences #FOS: Electrical engineering #Generalization #Initialization #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine learning #Mathematics #Meta learning (computer science) #Music and Audio Processing #One shot #Shot (pellet) #Sound (cs.SD) #Speech and Audio Processing #Speech recognition #Supervised learning #Task (project management) #Water Systems and Optimization #cs.LG #cs.SD #eess.AS #electronic engineering #information engineering #stat.ML
12. Newton vs the machine: solving the chaotic three-body problem using deep neural networks
    2019/10/16 by Philip G. Breen, Christopher N. Foley, Tjarda Boekholt +1 · 4 voices · 8 citations
    Computer Science · Mathematics · Physics and Astronomy · #Algorithm #Applied mathematics #Artificial intelligence #Artificial neural network #Chaotic #Computational Physics and Python Applications #Computer science #Discretization #Initialization #Integrator #Mathematical analysis #Mathematics #Model Reduction and Neural Networks #Phase space #Physics #Pulsars and Gravitational Waves Research #astro-ph.GA #astro-ph.SR #cs.LG #physics.comp-ph
13. Extended-range statistical ENSO prediction through operator-theoretic techniques for nonlinear dynamics
    2019/06/22 by Xinyang Wang, Joanna Slawinska, Joanna Sławińska +4 · 2 citations
    Earth and Planetary Sciences · Environmental Science · Mathematics · Physics and Astronomy · #Artificial intelligence #Atmospheric and Oceanic Physics (physics.ao-ph) #Benchmark (surveying) #Chaotic #Climate variability and models #Climatology #Computer science #Data Analysis #Econometrics #El Niño Southern Oscillation #FOS: Physical sciences #Forecast skill #Geography #Initialization #La Niña #Mathematics #Meteorological Phenomena and Simulations #Meteorology #Nonlinear system #Oceanographic and Atmospheric Processes #Predictability #Statistics #Statistics and Probability (physics.data-an) #physics.ao-ph #physics.data-an
14. Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization
    2019/02/15 by Hesham Mostafa, Xin Wang, Mostafa, Hesham +1 · 11 citations
    Computer Science · Mathematics · #Advanced Neural Network Applications #Algorithm #Artificial intelligence #Artificial neural network #Computer science #Convolutional neural network #Deep learning #Deep neural networks #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Generalization #Initialization #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Machine learning #Mathematics #Neural Networks and Applications #Pruning #cs.LG #stat.ML
15. Breaking Reversibility Accelerates Langevin Dynamics for Global Non-Convex Optimization
    2018/12/19 by Xuefeng Gao, Mert Gürbüzbalaban, Gao, Xuefeng +3 · 3 citations
    Computer Science · Engineering · Mathematics · #65C30 #65K05 #82C31 #90C26 #90C30 #Applied mathematics #Computer science #Eigenvalues and eigenvectors #FOS: Computer and information sciences #FOS: Mathematics #Gaussian Processes and Bayesian Inference #Geometry #Hessian matrix #Initialization #Langevin dynamics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Markov Chains and Monte Carlo Methods #Mathematical analysis #Mathematical optimization #Mathematics #Maxima and minima #Numerical Analysis (math.NA) #Optimization and Control (math.OC) #Physics #Probability (math.PR) #Quadratic equation #Quantum mechanics #Saddle point #Sparse and Compressive Sensing Techniques #Statistical physics
16. Implementing Neural Turing Machines
    2018/07/23 by Mark Collier, Joeran Beel, Collier, Mark +1 · 1 voice · 2 citations
    Computer Science · Engineering · Mathematics · #Algorithm #Artificial intelligence #Artificial neural network #Auxiliary memory #Class (philosophy) #Computation #Computer hardware #Computer science #Domain Adaptation and Few-Shot Learning #Ferroelectric and Negative Capacitance Devices #Initialization #Machine Learning and Algorithms #Machine learning #Programming language #Scheme (mathematics) #Turing #Turing machine #cs.LG #stat.ML
17. Real-Time End-to-End Action Detection with Two-Stream Networks
    2018/02/23 by Alaaeldin El-Nouby, Graham W. Taylor, El-Nouby, Alaaeldin +1 · 1 citation
    Computer Science · #Action (physics) #Advanced Neural Network Applications #Algorithm #Anomaly Detection Techniques and Applications #Artificial intelligence #Computation #Computer Vision and Pattern Recognition (cs.CV) #Computer network #Computer science #Data stream mining #End-to-end principle #FOS: Computer and information sciences #Flow (mathematics) #Human Pose and Action Recognition #Image (mathematics) #Initialization #Machine learning #Optical flow #Pipeline (software) #Real-time computing #STREAMS #Task (project management) #cs.CV
18. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
    2015/02/06 by Kaiming He, Xiangyu Zhang, He, Kaiming +5 · 3 voices · 567 citations
    Computer Science · Mathematics · #Advanced Neural Network Applications #Artificial intelligence #Artificial neural network #Bundle #Computer science #Contextual image classification #Convolutional neural network #Deep neural networks #Domain Adaptation and Few-Shot Learning #Image (mathematics) #Initialization #Machine learning #Mathematics #Overfitting #Parametric statistics #Pattern recognition (psychology) #Rectifier (neural networks) #Recurrent neural network #Scratch #Visual Attention and Saliency Detection #cs.AI #cs.CV #cs.LG
19. Phase Retrieval via Wirtinger Flow: Theory and Algorithms
    2015/02/03 by Emmanuel J. Candès, Xiaodong Li, Mahdi Soltanolkotabi · 69 citations
    Biochemistry, Genetics and Molecular Biology · Computer Science · Physics and Astronomy · #Advanced Electron Microscopy Techniques and Applications #Advanced X-ray Imaging Techniques #Computational complexity theory #Gradient descent #Initialization #Iterated function #Optical measurement and interference techniques #Phase (matter) #Phase retrieval #Scheme (mathematics) #Sequence (biology)
20. Let a biogeography-based optimizer train your Multi-Layer Perceptron
    2014/02/03 by Seyedali Mirjalili, Seyed Mohammad Mirjalili, Andrew Lewis · 18 citations
    Computer Science · Mathematics · #Algorithm #Artificial intelligence #Artificial neural network #Backpropagation #Computer science #Convergence (economics) #Heuristic #Initialization #Machine Learning and ELM #Machine learning #Mathematical optimization #Mathematics #Maxima and minima #Metaheuristic Optimization Algorithms Research #Multilayer perceptron #Neural Networks and Applications #Perceptron
21. The coupled 3D wave packet approach for triatomic reactive scattering in hyperspherical coordinates
    2012/09/05 by Satrajit Adhikari, A. J. C. Varandas, António J.C. Varandas · 2 citations
    Biochemistry, Genetics and Molecular Biology · Mathematics · Physics and Astronomy · #Advanced Chemical Physics Studies #Angular momentum #Atomic and Molecular Physics #Classical mechanics #Computer science #Coordinate system #Electron Spin Resonance Studies #Geometry #Initialization #Mathematical analysis #Mathematics #Physics #Quantum mechanics #Rotation (mathematics) #Scattering #Transformation (genetics) #Triatomic molecule #Wave packet
22. Proof of Finite Surface Code Threshold for Matching
    2012/06/30 by Austin G. Fowler · 3 citations
    Computer Science · Physics and Astronomy · #Algorithm #Computation #Computer science #Initialization #Physics #Quantum #Quantum Computing Algorithms and Architecture #Quantum Information and Cryptography #Quantum algorithm #Quantum computer #Quantum error correction #Quantum mechanics #Quantum-Dot Cellular Automata #Qubit #Word error rate #quant-ph
23. K-MLE: A fast algorithm for learning statistical mixture models
    2012/03/01 by Frank Nielsen · 1 citation
    Computer Science · Mathematics · #Advanced Clustering Algorithms Research #Algorithm #Applied mathematics #Artificial intelligence #Bayesian Methods and Mixture Models #Computer science #Estimator #Expectation–maximization algorithm #Exponential family #Exponential function #Gaussian #Image Retrieval and Classification Techniques #Initialization #Mathematics #Maximum likelihood #Mixture model #Pattern recognition (psychology) #Physics #Statistical model #Statistics #cs.LG #stat.ML
24. A Distributed Algorithm for Computing the Node Search Number in Trees
    2011/05/06 by David Coudert, Florian Huc, Dorian Mazauric · 1 citation
    Computer Science · Mathematics · #Advanced Graph Theory Research #Algorithm #Asynchronous communication #B-tree #Binary search tree #Binary tree #Combinatorics #Complexity and Algorithms in Graphs #Computation #Computer science #Data structure #Distributed algorithm #Distributed computing #Initialization #Interconnection Networks and Systems #Mathematics #Node (physics) #Search algorithm #Search tree #Theoretical computer science #Theory of computation #Tree (set theory) #Weight-balanced tree
25. Initialization of ice-sheet forecasts viewed as an inverse Robin problem
    2010/01/01 by Robert J. Arthern, G. Hilmar Gudmundsson · 5 citations
    Earth and Planetary Sciences · Environmental Science · Mathematics · #Boundary (topology) #Computer science #Cryospheric studies and observations #Flow (mathematics) #Geology #Geometry #Initialization #Inverse problem #Landslides and related hazards #Mathematical analysis #Mathematical optimization #Mathematics #Mechanics #Numerical methods in inverse problems #Physics #Solver #Stokes flow
26. Distributed quantum computation based on small quantum registers
    2007/09/30 by Liang Jiang, Jacob M. Taylor, Anders S. Sørensen +1 · 5 citations
    Computer Science · Mathematics · Physics and Astronomy · #Algorithm #Computer science #Initialization #Mathematics #Overhead (engineering) #Physics #Quantum #Quantum Computing Algorithms and Architecture #Quantum Information and Cryptography #Quantum and electron transport phenomena #Quantum computer #Quantum entanglement #Quantum mechanics #Topology (electrical circuits) #quant-ph
27. Generating and characterizing the perfect elimination orderings of a chordal graph
    2003/05/19 by L. Sunil Chandran, L.S. Chandran, L. Ibarra +5 · 2 citations
    Computer Science · Mathematics · #Advanced Graph Theory Research #Algorithm #Amortized analysis #Chordal graph #Clique #Combinatorics #Computer science #Constant (computer programming) #Constraint Satisfaction and Optimization #Data structure #Discrete mathematics #Graph #Graph theory and applications #Initialization #Line graph #Mathematics #Oracle #Pathwidth #Treewidth
28. Unsupervised learning of finite mixture models
    2002/03/01 by Mário A. T. Figueiredo, Anil K. Jain · 3 citations
    Computer Science · Mathematics · #Bayesian Methods and Mixture Models #Machine Learning and Algorithms #Target Tracking and Data Fusion in Sensor Networks #Mixture model #Expectation–maximization algorithm #Initialization #Computer science #Model selection #Unsupervised learning #Artificial intelligence #Convergence (economics) #Gaussian process #Parametric statistics #Algorithm #Pattern recognition (psychology) #Gaussian #Mathematics #Maximum likelihood
29. Generalized quantum search Hamiltonian
    2001/10/31 by Joonwoo Bae, Younghun Kwon · 1 citation
    Computer Science · Mathematics · Physics and Astronomy · #Combinatorics #Computer science #Hamiltonian (control theory) #Hamiltonian path #Hamiltonian path problem #Initialization #Mathematical optimization #Mathematical physics #Mathematics #Physics #Quantum #Quantum Computing Algorithms and Architecture #Quantum Information and Cryptography #Quantum many-body systems #Quantum mechanics #Theoretical physics #quant-ph
30. Robust text-independent speaker identification using Gaussian mixture speaker models
    1995/01/01 by D.A. Reynolds, Richard C. Rose · 2 citations
    Computer Science · #Speech Recognition and Synthesis #Speech and Audio Processing #Music and Audio Processing #Speech recognition #Computer science #Mixture model #Robustness (evolution) #Speaker recognition #Speaker identification #Gaussian #Initialization #Population #Pattern recognition (psychology) #Artificial intelligence

more