Lechao Xiao
- Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
2019/02/18 by Jaehoon Lee, Lechao Xiao, Samuel S. Schoenholz +4 · 2 voices · 12 citations
Mathematics · Computer Science · #stat.ML #cs.LG
- Scaling Exponents Across Parameterizations and Optimizers
2024/07/08 by Katie Everett, Everett, Katie, Lechao Xiao +19 · 2 voices · 20 citations
#cs.LG
- Gemma 4 Technical Report
2026/07/02 by Gemma Team, Sherif El Abd, Vaibhav Aggarwal +320 · 7 voices · 8 citations
#cs.CL #cs.AI
- Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models
2023/12/11 by Avi Singh, John D. Co-Reyes, Singh, Avi +76 · 37 citations
Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification #Natural Language Processing Techniques #Topic Modeling
- Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks
2018/06/14 by Lechao Xiao, Xiao, Lechao, Yasaman Bahri +7 · 29 citations
Computer Science · #Generative Adversarial Networks and Image Synthesis #Advanced Neural Network Applications #Human Pose and Action Recognition
- Small-scale proxies for large-scale Transformer training instabilities
2023/09/25 by Mitchell Wortsman, Wortsman, Mitchell, Peter J. Liu +29 · 27 citations
Computer Science · Decision Sciences · #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Forecasting Techniques and Applications #Gaussian Processes and Bayesian Inference #Machine Learning (cs.LG)
- Bayesian Deep Convolutional Networks with Many Channels are Gaussian\n Processes
2018/10/11 by Roman Novak, Novak, Roman, Lechao Xiao +16 · 22 citations
Computer Science · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Neural and Evolutionary Computing (cs.NE)
- Dataset Distillation with Infinitely Wide Convolutional Networks
2021/07/27 by Timothy Nguyen, Nguyen, Timothy, Roman Novak +5 · 16 citations
Computer Science · #Advanced Neural Network Applications #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification
- 4+3 Phases of Compute-Optimal Neural Scaling Laws
2024/05/23 by Elliot Paquette, Courtney Paquette, Paquette, Elliot +5 · 21 citations
Computer Science · #Neural Networks and Applications
- Neural Tangents: Fast and Easy Infinite Neural Networks in Python
2019/12/05 by Roman Novak, Lechao Xiao, Novak, Roman +11 · 12 citations
Physics and Astronomy · Computer Science · #Model Reduction and Neural Networks #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning
- Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networks
2020/01/16 by Wei Hu, Hu, Wei, Lechao Xiao +3 · 6 citations
Computer Science · #Speech Recognition and Synthesis #Neural Networks and Applications #Gaussian Processes and Bayesian Inference
- Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks
2025/07/02 by Shikai Qiu, Lechao Xiao, Qiu, Shikai +7 · 3 voices · 11 citations
#cs.LG
- The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks
2020/06/25 by Wei Hu, Lechao Xiao, Hu, Wei +5 · 2 citations
Computer Science · #Stochastic Gradient Optimization Techniques #Machine Learning and Algorithms #Neural Networks and Applications
- Higher decay inequalities for multilinear oscillatory integrals
2016/11/30 by Maxim Gilula, Philip T. Gressman, Gilula, Maxim +3 · 1 citation
Mathematics · #42B20 #Advanced Harmonic Analysis Research #Classical Analysis and ODEs (math.CA) #FOS: Mathematics #Nonlinear Partial Differential Equations #Spectral Theory in Mathematical Physics