Iclr2020: Compression based bound for non-compressed network

$ 28.00

4.5 (761) In stock

Iclr2020: Compression based bound for non-compressed network: unified generalization error analysis of large compressible deep neural network - Download as a PDF or view online for free
1) The document presents a new compression-based bound for analyzing the generalization error of large deep neural networks, even when the networks are not explicitly compressed. 2) It shows that if a trained network's weights and covariance matrices exhibit low-rank properties, then the network has a small intrinsic dimensionality and can be efficiently compressed. 3) This allows deriving a tighter generalization bound than existing approaches, providing insight into why overparameterized networks generalize well despite having more parameters than training examples.

ICML 2022

How does unlabeled data improve generalization in self training

On the Resilience of Deep Learning for reduced-voltage FPGAs

PAC-Bayesian Bound for Gaussian Process Regression and Multiple Kernel Additive Model

NeurIPS2020 (spotlight)] Generalization bound of globally optimal non convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics

Iclr2020: Compression based bound for non-compressed network: unified generalization error analysis of large compressible deep neural network

HyperDeepONet: learning operator with complex target function space using the limited resources via hypernetwork

A gradient optimization and manifold preserving based binary neural network for point cloud - ScienceDirect

Perception & Robotics Group at UMD

Discrete MRF Inference of Marginal Densities for Non-uniformly Discretized Variable Space

Continuum Modeling and Control of Large Nonuniform Networks

Meta-Learning with Implicit Gradients

Meta-Learning with Implicit Gradients