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.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “Nédélec”

Robust Training with Ensemble Consensuscs.LG

LEC prevents deep nets from memorizing noisy examples.

problem Deep nets overfit to noisy data.

method LEC removes noisy examples based on an ensemble of perturbed networks.

result LTEC outperforms state-of-the-art on noisy MNIST, CIFAR-10, and CIFAR-100.

deep learning ensemble label noise overfitting memorization

2019-10-22abs ↗pdf ↗

Detecting Adversarial Examples in Learning-Enabled Cyber-Physical Systems using Variational Autoencoder for Regressioncs.LG

The paper detects adversarial examples in LECs for regression in CPS using variational autoencoder.

problem Detecting adversarial examples in learning-enabled cyber-physical systems (CPS).

method Inductive conformal prediction using a variational autoencoder regression model.

result The method effectively detects adversarial examples with a short delay in an emergency braking system simulation.

adversarial examples cyber-physical systems learning-enabled components variational autoencoder regression

2020-03-21abs ↗pdf ↗

Trusted Confidence Bounds for Learning Enabled Cyber-Physical Systemscs.LG

The paper presents a method to compute trusted confidence bounds for LECs in CPS.

problem Non-transparent predictions of LECs make CPS safety challenging.

method Inductive Conformal Prediction (ICP) and Triplet Network architecture.

result Efficient real-time computation of trusted confidence bounds.

Cyber-Physical Systems Learning Enabled Components Deep Neural Networks Confidence Bounds Inductive Conformal Prediction

2020-03-11abs ↗pdf ↗

On Optimal Caching and Model Multiplexing for Large Model Inferencecs.LG

This paper optimizes caching and model multiplexing for large model inference.

problem Resource consumption and latency challenges in large model deployment.

method Jointly optimizing a caching algorithm (GDSF or LEC) and a model multiplexer for large model inference.

result Achieves optimal rates in offline and online settings with up to 50x improvement over baseline.

large language models model inference resource consumption cache optimization model multiplexing

2023-06-03abs ↗pdf ↗