290 citations · 701 across the 29 of their papers we have counts for
14 papers · 1 filter
Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks
Shikai Qiu, Lechao Xiao, Andrew Gordon Wilson +2
What scaling limits govern neural network training dynamics when model size and training time grow in tandem? We show that despite the complex interactions between architecture, tr…
Rethinking Conventional Wisdom in Machine Learning: From Generalization to Scaling
Lechao Xiao
The remarkable success of large language pretraining and the discovery of scaling laws signify a paradigm shift in machine learning. Notably, the primary objective has evolved from…
Scaling Exponents Across Parameterizations and Optimizers
Katie Everett, Lechao Xiao, Mitchell Wortsman +8
Robust and effective scaling of models from small to large width typically requires the precise adjustment of many algorithmic and architectural details, such as parameterization a…
Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models
Avi Singh, John D. Co-Reyes, Rishabh Agarwal +38
Fine-tuning language models~(LMs) on human-generated data remains a prevalent practice. However, the performance of such models is often limited by the quantity and diversity of hi…
Small-scale proxies for large-scale Transformer training instabilities
Mitchell Wortsman, Peter J. Liu, Lechao Xiao +13
Teams that have trained large Transformer-based models have reported training instabilities at large scale that did not appear when training with the same hyperparameters at smalle…
Fast Neural Kernel Embeddings for General Activations
Insu Han, Amir Zandieh, Jaehoon Lee +3
Infinite width limit has shed light on generalization and optimization aspects of deep learning by establishing connections between neural networks and kernel methods. Despite thei…
Synergy and Symmetry in Deep Learning: Interactions between the Data, Model, and Inference Algorithm
Lechao Xiao, Jeffrey Pennington
Although learning in high dimensions is commonly believed to suffer from the curse of dimensionality, modern machine learning methods often exhibit an astonishing power to tackle a…
Precise Learning Curves and Higher-Order Scaling Limits for Dot Product Kernel Regression
Lechao Xiao, Hong Hu, Theodor Misiakiewicz +2
As modern machine learning models continue to advance the computational frontier, it has become increasingly important to develop precise estimates for expected performance improve…
Eigenspace Restructuring: a Principle of Space and Frequency in Neural Networks
Lechao Xiao
Understanding the fundamental principles behind the massive success of neural networks is one of the most important open questions in deep learning. However, due to the highly comp…
Dataset Distillation with Infinitely Wide Convolutional Networks
Timothy Nguyen, Roman Novak, Lechao Xiao +1
The effectiveness of machine learning algorithms arises from being able to extract useful features from large amounts of data. As model and dataset sizes increase, dataset distilla…
Finite Versus Infinite Neural Networks: an Empirical Study
Jaehoon Lee, Samuel S. Schoenholz, Jeffrey Pennington +4
We perform a careful, thorough, and large scale empirical study of the correspondence between wide neural networks and kernel methods. By doing so, we resolve a variety of open que…
The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks
Wei Hu, Lechao Xiao, Ben Adlam +1
Modern neural networks are often regarded as complex black-box functions whose behavior is difficult to understand owing to their nonlinear dependence on the data and the nonconvex…
Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networks
Wei Hu, Lechao Xiao, Jeffrey Pennington
The selection of initial parameter values for gradient-based optimization of deep neural networks is one of the most impactful hyperparameter choices in deep learning systems, affe…
Disentangling Trainability and Generalization in Deep Neural Networks
Lechao Xiao, Jeffrey Pennington, Samuel S. Schoenholz
A longstanding goal in the theory of deep learning is to characterize the conditions under which a given neural network architecture will be trainable, and if so, how well it might…