paper-with-me

Papers

Tight Frame Contractions in Deep Networks

2021-01-01 · ICLR 2021 1 · John Zarka, Florentin Guth, Stéphane Mallat

Numerical experiments demonstrate that deep neural networks classifiers progressively separate class distributions around their mean, achieving linear separability. To explain this mechanism, we introduce structured deep network architectures that can be analyzed mathematically and have high classification accuracies on complex image databases. They iterate over tight frame contractions, which apply a pointwise contraction on decomposition coefficients in a tight frame. Tight frame contractions can reduce within-class variabilities while preserving class mean separations and hence improve the Fisher discriminant ratio. Variance reduction bounds are proved for soft-thresholding contractions with Gaussian mixture models. Iterating on tight frame contractions defines deep convolutional network without bias parameters in hidden layers. We show that spatial filters do not need to be learned, and can be defined from wavelet frames. Learning frame contractions along the resulting wavelet scattering channels is sufficient to nearly reach the classification accuracies of VGG-11 and ResNet-18 on ImageNet, with no learned bias.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

At-the-Roofline Sparse Tensor Contractions on Vector Processors for Transformer Inference

2026-07-28 · Bowen Wang, Chi Zhang, Diyou Shen, Renzo Andri 외 arxiv

Fine-grained weight pruning and activation sparsification have emerged as effective approaches for reducing the compute and memory cost of inference for Transformer models. In the moderate-sparsity regime, Gustavson's da…

ABB-BERT: A BERT model for disambiguating abbreviations and contractions

2022-07-08 · ICON 2021 12 · Prateek Kacker, Andi Cupallari, Aswin Gridhar Subramanian, Nimit Jain

Abbreviations and contractions are commonly found in text across different domains. For example, doctors' notes contain many contractions that can be personalized based on their choices. Existing spelling correction mode…

Spelling Correction

Estimating Sparse Discrete Distributions Under Local Privacy and Communication Constraints

2020-10-30 · Jayadev Acharya, Peter Kairouz, YuHan Liu, Ziteng Sun

We consider the problem of estimating sparse discrete distributions under local differential privacy (LDP) and communication constraints. We characterize the sample complexity for sparse estimation under LDP constraints …

Dynamic industry uncertainty networks and the business cycle

2021-01-18 · Jozef Barunik, Mattia Bevilacqua, Robert Faff

We argue that uncertainty network structures extracted from option prices contain valuable information for business cycles. Classifying U.S. industries according to their contribution to system-related uncertainty across…

Recovering the Structural Observability of Composite Networks via Cartesian Product

2020-01-14

Observability is a fundamental concept in system inference and estimation. This paper is focused on structural observability analysis of Cartesian product networks. Cartesian product networks emerge in variety of applica…