paper-with-me

Papers

A Johnson-Lindenstrauss Framework for Randomly Initialized CNNs

2021-09-29 · ICLR 2022 4 · Ido Nachum, Jan Hazla, Michael Gastpar, Anatoly Khina

How does the geometric representation of a dataset change after the application of each randomly initialized layer of a neural network? The celebrated Johnson-Lindenstrauss lemma answers this question for linear fully-connected neural networks (FNNs), stating that the geometry is essentially preserved. For FNNs with the ReLU activation, the angle between two input contracts according to a known mapping. The question for non-linear convolutional neural networks (CNNs) becomes much more intricate. To answer this question, we introduce a geometric framework. For linear CNNs, we show that the Johnson--Lindenstrauss lemma continues to hold, namely, that the angle between two inputs is preserved. For CNNs with ReLU activation, on the other hand, the behavior is richer: The angle between the outputs contracts, where the level of contraction depends on the nature of the inputs. In particular, after one layer, the geometry of natural images is essentially preserved, whereas for Gaussian correlated inputs, CNNs exhibit the same contracting behavior as FNNs with ReLU activation.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

LEMMA

Similar Papers 제목 키워드 기반

A Johnson--Lindenstrauss Framework for Randomly Initialized CNNs

2021-11-03 · Ido Nachum, Jan Hązła, Michael Gastpar, Anatoly Khina

How does the geometric representation of a dataset change after the application of each randomly initialized layer of a neural network? The celebrated Johnson--Lindenstrauss lemma answers this question for linear fully-c…

LEMMA

Johnson-Lindenstrauss Lemma, Linear and Nonlinear Random Projections, Random Fourier Features, and Random Kitchen Sinks: Tutorial and Survey

2021-08-09 · Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray, Mark Crowley

This is a tutorial and survey paper on the Johnson-Lindenstrauss (JL) lemma and linear and nonlinear random projections. We start with linear random projection and then justify its correctness by JL lemma and its proof. …

Dimensionality ReductionLEMMA

Private Query Release via the Johnson-Lindenstrauss Transform

2022-08-15 · Aleksandar Nikolov

We introduce a new method for releasing answers to statistical queries with differential privacy, based on the Johnson-Lindenstrauss lemma. The key idea is to randomly project the query answers to a lower dimensional spa…

LEMMA

An Introduction to Johnson-Lindenstrauss Transforms

2021-02-28 · Casper Benjamin Freksen

Johnson--Lindenstrauss Transforms are powerful tools for reducing the dimensionality of data while preserving key characteristics of that data, and they have found use in many fields from machine learning to differential…

BIG-bench Machine Learning

Dimensionality reduction with subgaussian matrices: a unified theory

2014-02-17 · Sjoerd Dirksen

We present a theory for Euclidean dimensionality reduction with subgaussian matrices which unifies several restricted isometry property and Johnson-Lindenstrauss type results obtained earlier for specific data sets. In p…

Dimensionality Reduction