How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks...

[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

Provable Tempered Overfitting of Minimal Nets and Typical Nets‏

I Harel, WM Hoza, G Vardi, I Evron, N Srebro… - arxiv preprint arxiv …, 2024‏ - arxiv.org‏
We study the overfitting behavior of fully connected deep Neural Networks (NNs) with binary
weights fitted to perfectly classify a noisy training set. We consider interpolation using both …‏
שמור צטט צוטט על ידי 1 מאמרים בנושא זה פתיחה בתור HTML
[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels‏

Y Slutzky, Y Alexander, N Razin, N Cohen - arxiv preprint arxiv …, 2024‏ - arxiv.org‏
Neural networks are powered by an implicit bias: a tendency of gradient descent to fit
training data in a way that generalizes to unseen data. A recent class of neural network …‏
שמור צטט מאמרים בנושא זה כל 2 הגרסאות פתיחה בתור HTML
[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes‏

D Qiao, K Zhang, E Singh, D Soudry… - arxiv preprint arxiv …, 2024‏ - arxiv.org‏
We study the generalization of two-layer ReLU neural networks in a univariate
nonparametric regression problem with noisy labels. This is a problem where kernels …‏
שמור צטט צוטט על ידי 4 מאמרים בנושא זה כל 2 הגרסאות פתיחה בתור HTML