List your company

Image Classification on MNIST (test) (Calibration Metrics)

95.3AccuracyRLA
54.84465.34775.8586.353May 14, 2026

Evaluation results

MethodLinks
RLAHessian approximation type=low-rank, Backbone=LeNet, Number of parameter samples=1002026.0595.30.6090.0090.0420.472
DIMSHessian approximation type=low-rank, Backbone=LeNet, Number of parameter samples=100, friction coefficient η0=0.12026.05950.2710.0080.0350.379
LINLAHessian approximation type=low-rank, Backbone=LeNet, Number of parameter samples=1002026.05862.6080.0260.1270.508
LAHessian approximation type=low-rank, Backbone=LeNet, Number of parameter samples=1002026.0556.411.5020.0830.4080.614