paper-with-me

Papers

Tensor Programs IVb: Adaptive Optimization in the Infinite-Width Limit

2023-08-03 · Greg Yang, Etai Littwin

Going beyond stochastic gradient descent (SGD), what new phenomena emerge in wide neural networks trained by adaptive optimizers like Adam? Here we show: The same dichotomy between feature learning and kernel behaviors (as in SGD) holds for general optimizers as well, including Adam -- albeit with a nonlinear notion of "kernel." We derive the corresponding "neural tangent" and "maximal update" limits for any architecture. Two foundational advances underlie the above results: 1) A new Tensor Program language, NEXORT, that can express how adaptive optimizers process gradients into updates. 2) The introduction of bra-ket notation to drastically simplify expressions and calculations in Tensor Programs. This work summarizes and generalizes all previous results in the Tensor Programs series of papers.

📄 PDF Abstract BibTeX arXiv:2308.01814

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Adam 설명 없음

Similar Papers 제목 키워드 기반

Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics

2021-05-08 · Greg Yang, Etai Littwin

Yang (2020a) recently showed that the Neural Tangent Kernel (NTK) at initialization has an infinite-width limit for a large class of architectures including modern staples such as ResNet and Transformers. However, their …

Quantitative Gaussian-Process limits of Tensor Programs

2026-07-07 · Andrea Agazzi, Eloy Mosig García, Dario Trevisan arxiv

We study the infinite-width Gaussian-process limit of random neural networks through the lens of tensor programs, and we provide a quantitative convergence theory in Wasserstein distance. Our main result gives explicit f…

Feature Learning in Infinite-Width Neural Networks

2020-11-30 · Greg Yang, Edward J. Hu

As its width tends to infinity, a deep neural network's behavior under gradient descent can become simplified and predictable (e.g. given by the Neural Tangent Kernel (NTK)), if it is parametrized appropriately (e.g. the…

Few-Shot LearningTransfer Learning

Tensor Programs VI: Feature Learning in Infinite-Depth Neural Networks

2023-10-03 · Greg Yang, Dingli Yu, Chen Zhu, Soufiane Hayou

By classifying infinite-width neural networks and identifying the *optimal* limit, Tensor Programs IV and V demonstrated a universal way, called $\mu$P, for *widthwise hyperparameter transfer*, i.e., predicting optimal h…

Diversity

Efficient Computation of Deep Nonlinear Infinite-Width Neural Networks that Learn Features

2021-09-29 · ICLR 2022 4 · Greg Yang, Michael Santacroce, Edward J Hu

While a popular limit of infinite-width neural networks, the Neural Tangent Kernel (NTK) often exhibits performance gaps from finite-width neural networks on standard datasets, due to lack of feature learning. Although t…