AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregation

Shashank Rajput, Hongyi Wang, Zachary Charles, Dimitris Papailiopoulos

NeurIPS 2019 · Learning theory and algorithms › Prediction and decision losses · approach: Determinantal point process inference · 14 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add DETOX filtering and hierarchical aggregation to Multi-KrumMulti-Krum · CIFAR-10, ResNet-18, ALIEtest accuracy: 45.24% -> 80.3%Improved
Add DETOX filtering and hierarchical aggregation to BulyanBulyan · CIFAR-100, VGG13-BN, ALIEtest accuracy: 11.06% -> 46.82%Improved
Add DETOX filtering and hierarchical aggregation to coordinate-wise medianCoordinate-wise median · CIFAR-100, VGG13-BN, ALIEtest accuracy: 8.64% -> 59.51%Improved
Pair signSGD with DETOX's redundancy-based filteringsignSGD · CIFAR-10, ResNet-18, constant Byzantine attacktest accuracy: 34.92% -> 78.75%Improved
Pair signSGD with DETOX's redundancy-based filteringsignSGD · CIFAR-100, VGG13-BN, constant Byzantine attacktest accuracy (TOP-1): 2.12% -> 40.37%Improved
Add DETOX to coordinate-wise medianCoordinate-wise median · CIFAR-10, ResNet-18, reverse gradient attackspeedup to 90% test accuracy: 5×Improved
Use DETOX with robust aggregationRobust aggregators · Distributed training, CIFAR-10 and CIFAR-100 experimentsper-iteration speedup: up to 3×Improved
Use DETOX filtering and hierarchy with coordinate-wise medianCoordinate-wise median · CIFAR-10, ResNet-18, reverse gradient attacktest accuracyNo clear effect
Replace mean-at-first-level plus robust final aggregation with Multi-Krum at the first level and mean at the final level (ablation)DETOX hierarchical aggregation · Byzantine-resilience experimentstest accuracyImproved
Replace mean-at-first-level plus robust final aggregation with Bulyan at the first level and mean at the final level (ablation)DETOX hierarchical aggregation · Byzantine-resilience experimentstest accuracyImproved
Add redundancy-based majority filtering before robust aggregationRobust gradient aggregation · Synthetic robust mean estimationestimation errorImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy