conftrace_

2024 NeurIPS NeurIPS 2024

Learnability of high-dimensional targets by two-parameter models and gradient flow

Abstract

We explore the theoretical possibility of learning $d$-dimensional targets with $W$-parameter models by gradient flow (GF) when $W

Authors

Dmitry Yarotsky

Topics

Machine Learning > Optimization & Theory > Learning Theory Machine Learning > Optimization & Theory > Neural Network Optimization Deep Learning > Architectures > Neural Networks Deep Learning > Optimization & Theory > Neural Network Optimization Deep Learning > Optimization & Theory > Theory

Keywords

theoretical analysis neural network theory high-dimensional learning gradient flow neural network high-dimensional target parameter model parameter complexity

More from NeurIPS 2024

All NeurIPS 2024 papers →

Is Value Learning Really the Main Bottleneck in Offline RL?

VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance

ActSort: An active-learning accelerated cell sorting algorithm for large-scale calcium imaging datasets

UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation

Decision-Focused Learning with Directional Gradients

Bridging the Divide: Reconsidering Softmax and Linear Attention