Lechao Xiao
18 papers · 2018–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
🗺️ Taxonomy Completionist (30) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird
🤝
Dynamic Duo
(14)
🧭
Keyword Pioneer
🏆
Keyword Champion
(2)
👑
Triple Crown
⚡
Prolific Year · Productive
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
🗃️
Keyword Collector
(79)
Venues
Top co-authors
Research topics
Machine Learning
(18)
Optimization & Theory · Machine Learning
(18)
Deep Learning
(14)
Architectures
(9)
Optimization & Theory · Deep Learning
(5)
Artificial Intelligence
(3)
Computer Vision
(3)
Mathematics & Optimization
(3)
Core Methods
(3)
Models
(3)
Core AI · Computer Vision
(2)
Core AI · Artificial Intelligence
(2)
Optimization
(2)
Analysis
(1)
Application Areas
(1)
Keywords
convolutional neural network
(5)
neural tangent kernel
(5)
neural network
(3)
bayesian inference
(3)
infinite-width limit
(3)
gaussian process
(2)
neural kernel
(2)
convolutional network
(2)
neural network optimization
(2)
infinite-width network
(2)
neural scaling law
(2)
initialization scheme
(2)
kernel methods
(2)
linear model
(2)
generalization error
(2)
gradient descent
(2)
neural network gaussian process
(2)
monte carlo estimation
(1)
asymptotic analysis
(1)
theoretical analysis
(1)
Papers
Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks
ICML 2025
4+3 Phases of Compute-Optimal Neural Scaling Laws
NeurIPS 2024
Scaling Exponents Across Parameterizations and Optimizers
ICML 2024
Small-scale proxies for large-scale Transformer training instabilities
ICLR 2024
Eigenspace Restructuring: A Principle of Space and Frequency in Neural Networks
COLT 2022
Fast Neural Kernel Embeddings for General Activations
NeurIPS 2022
Precise Learning Curves and Higher-Order Scalings for Dot-product Kernel Regression
NeurIPS 2022
Synergy and Symmetry in Deep Learning: Interactions between the Data, Model, and Inference Algorithm
ICML 2022
Dataset Distillation with Infinitely Wide Convolutional Networks
NeurIPS 2021
Exploring the Uncertainty Properties of Neural Networks’ Implicit Priors in the Infinite-Width Limit
ICLR 2021
Disentangling Trainability and Generalization in Deep Neural Networks
ICML 2020
Finite Versus Infinite Neural Networks: an Empirical Study
NeurIPS 2020
Neural Tangents: Fast and Easy Infinite Neural Networks in Python
ICLR 2020
Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networks
ICLR 2020
The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks
NeurIPS 2020
Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes
ICLR 2019
Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
NeurIPS 2019
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks
ICML 2018