English
Related papers

Related papers: Training Infinitely Deep and Wide Transformers

200 papers

In deep learning theory, the covariance matrix of the representations serves as a proxy to examine the network's trainability. Motivated by the success of Transformers, we study the covariance matrix of a modified Softmax-based attention…

Machine Learning · Statistics 2023-12-12 Lorenzo Noci , Chuning Li , Mufan Bill Li , Bobby He , Thomas Hofmann , Chris Maddison , Daniel M. Roy

Implicit Neural Representations (INRs) have emerged and shown their benefits over discrete representations in recent years. However, fitting an INR to the given observations usually requires optimization with gradient descent from scratch,…

Machine Learning · Computer Science 2022-08-08 Yinbo Chen , Xiaolong Wang

In this paper, we advance the understanding of neural network training dynamics by examining the intricate interplay of various factors introduced by weight parameters in the initialization process. Motivated by the foundational work of Luo…

Machine Learning · Computer Science 2024-04-09 Yuqing Li , Tao Luo , Qixuan Zhou

Gradient based optimization is fundamental to most modern deep reinforcement learning algorithms, however, it introduces significant sensitivity to hyperparameters, unstable training dynamics, and high computational costs. We propose TabPFN…

Machine Learning · Computer Science 2025-09-16 David Schiff , Ofir Lindenbaum , Yonathan Efroni

Transformers have recently revolutionized many domains in modern machine learning and one salient discovery is their remarkable in-context learning capability, where models can solve an unseen task by utilizing task-specific prompts without…

Machine Learning · Computer Science 2023-10-10 Yu Huang , Yuan Cheng , Yingbin Liang

In this work, we analyze various scaling limits of the training dynamics of transformer models in the feature learning regime. We identify the set of parameterizations that admit well-defined infinite width and depth limits, allowing the…

Machine Learning · Statistics 2024-10-07 Blake Bordelon , Hamza Tahir Chaudhry , Cengiz Pehlevan

We propose a globally convergent multilevel training method for deep residual networks (ResNets). The devised method can be seen as a novel variant of the recursive multilevel trust-region (RMTR) method, which operates in hybrid…

Machine Learning · Computer Science 2022-06-14 Alena Kopaničáková , Rolf Krause

The Neural Tangent Kernel (NTK) viewpoint is widely employed to analyze the training dynamics of overparameterized Physics-Informed Neural Networks (PINNs). However, unlike the case of linear Partial Differential Equations (PDEs), we show…

Machine Learning · Computer Science 2024-11-01 Andrea Bonfanti , Giuseppe Bruno , Cristina Cipriani

Transformers perform inference by iteratively transforming token representations across layers. This layerwise computation has been studied empirically, and recent mean-field theories of Transformer dynamics explain how attention can drive…

Machine Learning · Computer Science 2026-05-11 Noboru Isobe , Daisuke Inoue , Masaaki Imaizumi

State-of-the-art neural networks require extreme computational power to train. It is therefore natural to wonder whether they are optimally trained. Here we apply a recent advancement in stochastic thermodynamics which allows bounding the…

Machine Learning · Statistics 2023-07-28 Inbar Seroussi , Alexander A. Alemi , Moritz Helias , Zohar Ringel

We present a new training methodology for transformers using a multilevel, layer-parallel approach. Through a neural ODE formulation of transformers, our application of a multilevel parallel-in-time algorithm for the forward and…

Machine Learning · Computer Science 2026-01-27 Shuai Jiang , Marc Salvadó-Benasco , Eric C. Cyr , Alena Kopaničáková , Rolf Krause , Jacob B. Schroder

To understand how deep learning works, it is crucial to understand the training dynamics of neural networks. Several interesting hypotheses about these dynamics have been made based on empirically observed phenomena, but there exists a…

Machine Learning · Statistics 2021-11-16 Nikhil Ghosh , Song Mei , Bin Yu

The performance and efficiency of distributed training of Deep Neural Networks highly depend on the performance of gradient averaging among all participating nodes, which is bounded by the communication between nodes. There are two major…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-02-10 Linnan Wang , Wei Wu , Junyu Zhang , Hang Liu , George Bosilca , Maurice Herlihy , Rodrigo Fonseca

How well does a classic deep net architecture like AlexNet or VGG19 classify on a standard dataset such as CIFAR-10 when its width --- namely, number of channels in convolutional layers, and number of nodes in fully-connected internal…

Machine Learning · Computer Science 2019-11-05 Sanjeev Arora , Simon S. Du , Wei Hu , Zhiyuan Li , Ruslan Salakhutdinov , Ruosong Wang

We theoretically characterize gradient descent dynamics in deep linear networks trained at large width from random initialization and on large quantities of random data. Our theory captures the ``wider is better" effect of…

Machine Learning · Computer Science 2025-06-17 Blake Bordelon , Cengiz Pehlevan

We prove that a randomly initialized neural network of *any architecture* has its Tangent Kernel (NTK) converge to a deterministic limit, as the network widths tend to infinity. We demonstrate how to calculate this limit. In prior…

Machine Learning · Statistics 2020-12-01 Greg Yang

Despite deep neural networks' powerful representation learning capabilities, theoretical understanding of how networks can simultaneously achieve meaningful feature learning and global convergence remains elusive. Existing approaches like…

Machine Learning · Computer Science 2025-07-23 Zixiang Chen , Greg Yang , Qingyue Zhao , Quanquan Gu

This paper approaches the unsupervised learning problem by gradient descent in the space of probability density functions. A main result shows that along the gradient flow induced by a distribution-dependent ordinary differential equation…

Machine Learning · Computer Science 2024-01-09 Yu-Jui Huang , Yuchong Zhang

This paper proposes a new mean-field framework for over-parameterized deep neural networks (DNNs), which can be used to analyze neural network training. In this framework, a DNN is represented by probability measures and functions over its…

Machine Learning · Statistics 2020-07-06 Cong Fang , Jason D. Lee , Pengkun Yang , Tong Zhang

Skip connections and normalisation layers form two standard architectural components that are ubiquitous for the training of Deep Neural Networks (DNNs), but whose precise roles are poorly understood. Recent approaches such as Deep Kernel…

Machine Learning · Computer Science 2023-02-22 Bobby He , James Martens , Guodong Zhang , Aleksandar Botev , Andrew Brock , Samuel L Smith , Yee Whye Teh