ResNEsts and DenseNEsts: Block-based DNN Models with Improved Representation Guarantees

by   Kuan-Lin Chen, et al.

Models recently used in the literature proving residual networks (ResNets) are better than linear predictors are actually different from standard ResNets that have been widely used in computer vision. In addition to the assumptions such as scalar-valued output or single residual block, these models have no nonlinearities at the final residual representation that feeds into the final affine layer. To codify such a difference in nonlinearities and reveal a linear estimation property, we define ResNEsts, i.e., Residual Nonlinear Estimators, by simply dropping nonlinearities at the last residual representation from standard ResNets. We show that wide ResNEsts with bottleneck blocks can always guarantee a very desirable training property that standard ResNets aim to achieve, i.e., adding more blocks does not decrease performance given the same set of basis elements. To prove that, we first recognize ResNEsts are basis function models that are limited by a coupling problem in basis learning and linear prediction. Then, to decouple prediction weights from basis learning, we construct a special architecture termed augmented ResNEst (A-ResNEst) that always guarantees no worse performance with the addition of a block. As a result, such an A-ResNEst establishes empirical risk lower bounds for a ResNEst using corresponding bases. Our results demonstrate ResNEsts indeed have a problem of diminishing feature reuse; however, it can be avoided by sufficiently expanding or widening the input space, leading to the above-mentioned desirable property. Inspired by the DenseNets that have been shown to outperform ResNets, we also propose a corresponding new model called Densely connected Nonlinear Estimator (DenseNEst). We show that any DenseNEst can be represented as a wide ResNEst with bottleneck blocks. Unlike ResNEsts, DenseNEsts exhibit the desirable property without any special architectural re-design.


page 1

page 2

page 3

page 4


Rethinking Bottleneck Structure for Efficient Mobile Network Design

The inverted residual block is dominating architecture design for mobile...

Representing the Special Linear Group with Block Unitriangular Matrices

We prove that every element of the special linear group can be represent...

Are deep ResNets provably better than linear predictors?

Recently, a residual network (ResNet) with a single residual block has b...

Are ResNets Provably Better than Linear Predictors?

A residual network (or ResNet) is a standard deep neural net architectur...

Auxiliary Loss of Transformer with Residual Connection for End-to-End Speaker Diarization

End-to-end neural diarization (EEND) with self-attention directly predic...

Robust learning with implicit residual networks

In this effort we propose a new deep architecture utilizing residual blo...

Unifying Nonlocal Blocks for Neural Networks

The nonlocal-based blocks are designed for capturing long-range spatial-...

Please sign up or login with your details

Forgot password? Click here to reset