Search Results for author:
Found 5 papers, 1 papers with code
Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs
Vision tasks are characterized by the properties of locality and translation invariance.
Applying statistical learning theory to deep learning
Although statistical learning theory provides a robust framework to understand supervised learning, many theoretical aspects of deep learning remain unclear, in particular how different architectures may lead to inductive bias when trained using gradient based methods.
Agnostic Learnability of Halfspaces via Logistic Loss
In this paper, we close this gap by constructing a well-behaved distribution such that the global minimizer of the logistic risk over this distribution only achieves $\Omega(\sqrt{\textrm{OPT}})$ misclassification risk, matching the upper bound in (Frei et al., 2021).
Local Signal Adaptivity: Provable Feature Learning in Neural Networks Beyond Kernels
We therefore propose the "local signal adaptivity" (LSA) phenomenon as one explanation for the superiority of neural networks over kernel methods.
PAC-Bayes Learning Bounds for Sample-Dependent Priors
We present a series of new PAC-Bayes learning guarantees for randomized algorithms with sample-dependent priors.
