Rizwan Qureshi

Rizwan Qureshi


Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
MAMohammed Alnemari
Mohammed Alnemari
RQRizwan Qureshi
Rizwan Qureshi
NBNader Bagherzadeh
Nader Bagherzadeh
Neural scaling laws describe how model performance improves as a power law with size, but existing work has focused almost entirely on models above 100 M parameters. The regime below 20 million parameters, where TinyML and edge AI systems operate, remains largely unexamined. We train 90 models spanning 22 K to 19.8 M parameters across two architecture families (a plain ConvNet and MobileNetV2) on CIFAR-100, varying width while holding depth and training protocol fixed. Both architectures follow approximate power laws, with exponents of α=0.156 (ScaleCNN) and α=0.106 (MobileNetV2). However, the power law does not hold uniformly: local exponents decay with scale, and MobileNetV2 saturates at 19.8 M parameters (αlocal=0.006), hitting a data wall. The structure of errors also changes with scale. The Jaccard overlap between error sets of the smallest and largest ScaleCNN models is only 0.35; compression changes which inputs are misclassified, not merely how many. Small models develop a triage strategy, concentrating capacity on easy classes (Gini of per-class accuracy: 0.26 at 22 K params vs. 0.09 at 4.7 M) while effectively abandoning the hardest ones (bottom-5 class accuracy: 10% vs. 53%). The smallest models achieve the lowest ECE values (0.013 vs. peak 0.110 at mid-size), reversing the typical overconfidence–capacity relationship, though this partly reflects a global-mean matching artifact rather than well-calibrated per-bin confidence. On CIFAR-100, aggregate accuracy alone is therefore a misleading basis for edge deployment decisions; validation must happen at the target model size. All findings in this study are based on CIFAR-100 (32 × 32, 100 classes); their generalizability to other datasets, resolutions, and architectures remains to be verified.