DeepAI AI Chat
Log In Sign Up

Separation Results between Fixed-Kernel and Feature-Learning Probability Metrics

06/10/2021
by   Carles Domingo Enrich, et al.
0

Several works in implicit and explicit generative modeling empirically observed that feature-learning discriminators outperform fixed-kernel discriminators in terms of the sample quality of the models. We provide separation results between probability metrics with fixed-kernel and feature-learning discriminators using the function classes ℱ_2 and ℱ_1 respectively, which were developed to study overparametrized two-layer neural networks. In particular, we construct pairs of distributions over hyper-spheres that can not be discriminated by fixed kernel (ℱ_2) integral probability metric (IPM) and Stein discrepancy (SD) in high dimensions, but that can be discriminated by their feature learning (ℱ_1) counterparts. To further study the separation we provide links between the ℱ_1 and ℱ_2 IPMs with sliced Wasserstein distances. Our work suggests that fixed-kernel discriminators perform worse than their feature learning counterparts because their corresponding metrics are weaker.

READ FULL TEXT

page 1

page 2

page 3

page 4

04/01/2015

A Theory of Feature Learning

Feature Learning aims to extract relevant information contained in data ...
12/28/2022

Feature learning in neural networks and kernel machines that recursively learn features

Neural networks have achieved impressive results on many technological a...
12/23/2022

The Onset of Variance-Limited Behavior for Networks in the Lazy and Rich Regimes

For small training set sizes P, the generalization error of wide neural ...
07/01/2021

Implicit Acceleration and Feature Learning in Infinitely Wide Neural Networks with Bottlenecks

We analyze the learning dynamics of infinitely wide neural networks with...
05/19/2022

Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks

We analyze feature learning in infinite width neural networks trained wi...
12/27/2021

Depth and Feature Learning are Provably Beneficial for Neural Network Discriminators

We construct pairs of distributions μ_d, ν_d on ℝ^d such that the quanti...
12/18/2014

Unsupervised Learning of Spatiotemporally Coherent Metrics

Current state-of-the-art classification and detection algorithms rely on...