paper-with-me

홈 › Papers

The Curse of Depth in Kernel Regime

2021-09-22 · NeurIPS Workshop ICBINB 2021 12 · Soufiane Hayou, Arnaud Doucet, Judith Rousseau

Recent work by Jacot et al. (2018) has shown that training a neural network of any kind with gradient descent is strongly related to kernel gradient descent in function space with respect to the Neural Tangent Kernel (NTK). Empirical results in (Lee et al., 2019) demonstrated high performance of a linearized version of training using the so-called NTK regime. In this paper, we show that the large depth limit of this regime is unexpectedly trivial, and we fully characterize the convergence rate to this trivial regime.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

NTK 설명 없음

Similar Papers 제목 키워드 기반

Breaking the curse of dimensionality with Isolation Kernel

2021-09-29 · Kai Ming Ting, Takashi Washio, Ye Zhu, Yang Xu

The curse of dimensionality has been studied in different aspects. However, breaking the curse has been elusive. We show for the first time that it is possible to break the curse using the recently introduced Isolation K…

Clustering

Finite Depth and Width Corrections to the Neural Tangent Kernel

2019-09-13 · ICLR 2020 1 · Boris Hanin, Mihai Nica

We prove the precise scaling, at finite depth and width, for the mean and variance of the neural tangent kernel (NTK) in a randomly initialized ReLU network. The standard deviation is exponential in the ratio of network …

On Random Kernels of Residual Architectures

2020-01-28 · Etai Littwin, Tomer Galanti, Lior Wolf

We derive finite width and depth corrections for the Neural Tangent Kernel (NTK) of ResNets and DenseNets. Our analysis reveals that finite size residual architectures are initialized much closer to the "kernel regime" t…

Solving Oversmoothing in GNNs via Nonlocal Message Passing: Algebraic Smoothing and Depth Scalability

2025-12-09 · Weiqi Guan, Junlin He arxiv

The relationship between Layer Normalization (LN) placement and the oversmoothing phenomenon remains underexplored. We identify a critical dilemma: Pre-LN architectures avoid oversmoothing but suffer from the curse of de…

Kernel and Rich Regimes in Overparametrized Models

2020-02-20 · Blake Woodworth, Suriya Gunasekar, Jason D. Lee, Edward Moroshko 외

A recent line of work studies overparametrized neural networks in the "kernel regime," i.e. when the network behaves during training as a kernelized linear predictor, and thus training with gradient descent has the effec…