On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

7 results for “ResNet-56”

A Framework for Neural Network Pruning Using Gibbs Distributionscs.LG

Gibbs pruning optimizes neural networks by combining physics and regularization.

problem Large neural networks are impractical for many applications.

method Combines statistical physics and stochastic regularization to train and prune networks simultaneously.

result Gibbs pruning achieves state-of-the-art performance on ResNet-56.

neural network pruning Gibbs distribution statistical physics stochastic regularization ResNet-56

2020-06-08abs ↗pdf ↗

Adversarially Training for Audio Classifierseess.AS

Adversarial training improves audio classifier robustness.

problem Improving robustness of audio classifiers against adversarial attacks.

method Adversarial training of deep neural networks on audio data.

result Adversarially trained models can resist higher perturbations and fooling rates.

adversarial training audio classification robustness deep learning adversarial attacks

2020-08-26abs ↗pdf ↗

CPOT: Channel Pruning via Optimal Transportcs.LG

CPOT prunes deep networks by identifying redundant filters using optimal transport.

problem Redundant filters in deep neural networks make models hard to deploy on resource-limited platforms.

method CPOT uses optimal transport to find the mean of channel distributions, pruning redundant information.

result CPOT outperforms state-of-the-art methods in pruning ResNet models and image-to-image translation tasks.

channel pruning optimal transport deep learning resource constraints image-to-image translation

2020-05-21abs ↗pdf ↗

Residual Networks as Nonlinear Systems: Stability Analysis using Linearizationcs.LG

We regard pre-trained residual networks (ResNets) as nonlinear systems and use linearization, a common method used in the qualitative analysis of nonlinear systems, to understand the behavior of the networks under small perturbations of the input images. We work with ResNet-56 and ResNet-110 trained on the CIFAR-10 dat…

2019-05-31abs ↗pdf ↗

A Gradient Flow Framework For Analyzing Network Pruningcs.LG

A new framework explains why early pruning works well.

problem Understanding why early pruning of neural networks leads to good performance.

method Gradient flow framework to unify pruning measures.

result Magnitude-based pruning removes least contributing parameters, leading to faster convergence.

network pruning gradient flow model evolution early training loss preservation

2020-09-24abs ↗pdf ↗

Evolution in Groups: A deeper look at synaptic cluster driven evolution of deep neural networkscs.NE

A promising paradigm for achieving highly efficient deep neural networks is the idea of evolutionary deep intelligence, which mimics biological evolution processes to progressively synthesize more efficient networks. A crucial design factor in evolutionary deep intelligence is the genetic encoding scheme used to simula…

2017-04-07abs ↗pdf ↗

Lessons from Generalization Error Analysis of Federated Learning: You May Communicate Less Often!stat.ML

Study shows more frequent communication in FL reduces model's generalization power.

problem Understanding how often clients should communicate with a server in federated learning.

method PAC-Bayes and rate-distortion theoretic bounds on generalization error.

result More frequent communication with the server decreases model's generalization power.

Federated Learning Generalization Error Communication Rounds Support Vector Machines PAC-Bayes

2023-06-09abs ↗pdf ↗