AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Dynamic Symmetric Point Tracking: Tackling Non-ideal Reference in Analog In-memory Training

Quan Xiao, Jindan Li, Zhaoxian Wu, Tayfun Gokmen, Tianyi Chen

ICML 2026 · Architectures and efficiency › RNNs and normalization · approach: Dataset condensation and flow estimation · 0 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
estimate SP dynamically during training (E-RIDER) instead of fixed referenceTT-v2 with zero reference · LeNet-5 MNIST, ref mean 0.4, std 1.0test accuracy: 67.08 -> 88.02Improved
add residual learning with moving-average SP tracking, chopping and mixed-weight gradient (E-RIDER) over AGADAGAD · FCN MNIST, ref mean 0.4, std 1.0test accuracy: 90.43 -> 95.14Improved
raise reference std from 0.05 to 1.0 (nonzero SP offset) (ablation)TT-v2 · FCN MNIST, ref mean 0.4test accuracy: 72.00 -> 57.79Hurt
raise reference std from 0.05 to 1.0 (nonzero SP offset) (ablation)E-RIDER · FCN MNIST, ref mean 0.4test accuracy: 96.07 -> 95.14Hurt
estimate SP with ZS using fewer pulses (N) before training (ablation)two-stage residual learning with ZS · LeNet-5 MNIST (TT-v1) training losstraining lossHurt
use ZS with N = 4000 pulses on a 2000-state device (ablation)two-stage ZS · LeNet-5 MNISTreaching training loss 0.2Hurt
use E-RIDER instead of two-stage ZSTT-v2 with ZS · LeNet-5 MNISTtotal pulse cost to reach loss 0.2Improved
decrease response granularity (higher-precision device) for ZS calibration (ablation)ZS algorithm · ReRAM arraypulses for 1% errorHurt
use small chopper probability p > 0 (ablation)E-RIDER · MNIST FCNtest accuracyImproved
evaluate E-RIDER on ResNet-18 CIFAR-100 with large SP offsetTT-v2 and AGAD · CIFAR-100 ResNet-18 (80 epochs)test accuracyImproved

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