paper-with-me

홈 › Papers

Overparameterization of deep ResNet: zero loss and mean-field analysis

2021-05-30 · Zhiyan Ding, Shi Chen, Qin Li, Stephen Wright

Finding parameters in a deep neural network (NN) that fit training data is a nonconvex optimization problem, but a basic first-order optimization method (gradient descent) finds a global optimizer with perfect fit (zero-loss) in many practical situations. We examine this phenomenon for the case of Residual Neural Networks (ResNet) with smooth activation functions in a limiting regime in which both the number of layers (depth) and the number of weights in each layer (width) go to infinity. First, we use a mean-field-limit argument to prove that the gradient descent for parameter training becomes a gradient flow for a probability distribution that is characterized by a partial differential equation (PDE) in the large-NN limit. Next, we show that under certain assumptions, the solution to the PDE converges in the training time to a zero-loss solution. Together, these results suggest that the training of the ResNet gives a near-zero loss if the ResNet is large enough. We give estimates of the depth and width needed to reduce the loss below a given threshold, with high probability.

📄 PDF Abstract BibTeX arXiv:2105.14417

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음
Batch Normalization 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Residual Connection 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…

Similar Papers 제목 키워드 기반

A Mean-field Analysis of Deep ResNet and Beyond: Towards Provable Optimization Via Overparameterization From Depth

2020-03-11 · Yiping Lu, Chao Ma, Yulong Lu, Jianfeng Lu 외

Training deep neural networks with stochastic gradient descent (SGD) can often achieve zero training loss on real-world tasks although the optimization landscape is known to be highly non-convex. To understand the succes…

A Mean-field Analysis of Deep ResNet and Beyond:Towards Provable Optimization Via Overparameterization From Depth

2020-02-26 · ICLR Workshop DeepDiffEq 2019 12 · Yiping Lu, Chao Ma, Yulong Lu, Jianfeng Lu 외

Training deep neural networks with stochastic gradient descent (SGD) can often achieve zero training loss on real-world tasks although the optimization landscape is known to be highly non-convex. To understand the succes…

A Mean Field Analysis Of Deep ResNet And Beyond: Towards Provably Optimization Via Overparameterization From Depth

2020-01-01 · ICML 2020 1 · Yiping Lu, Chao Ma, Yulong Lu, Jianfeng Lu 외

Training deep neural networks with stochastic gradient descent (SGD) can often achieve zero training loss on real-world tasks although the optimization landscape is known to be highly non-convex. To understand the succes…

Geometry and Local Recovery of Global Minima of Two-layer Neural Networks at Overparameterization

2023-09-01 · Leyang Zhang, Yaoyu Zhang, Tao Luo

Under mild assumptions, we investigate the geometry of the loss landscape for two-layer neural networks in the vicinity of global minima. Utilizing novel techniques, we demonstrate: (i) how global minima with zero genera…

How Does Overparameterization Affect Features?

2024-07-01 · Ahmet Cagri Duzgun, Samy Jelassi, Yuanzhi Li

Overparameterization, the condition where models have more parameters than necessary to fit their training loss, is a crucial factor for the success of deep learning. However, the characteristics of the features learned …