2026-10-09 · America/Los_Angeles · 社区动态 · #10

I built MaRN: a PyTorch library for training neural networks through low-dimensional parameter mappings [P]

I built MaRN (Mapping Networks), a PyTorch library that lets you optimize a compact latent representation instead of directly training every model parameter. Some results from my current benchmarks: MNIST CNN: Reduced a 537,748-parameter CNN to 4,080 trainable parameters (131.8× reduction), with accuracy decreasing from 99.07% → 98.10% (−0.97 pp). A smaller 107,998-parameter CNN was reduced to 1,872 trainable parameters (57.7× reduction), with accuracy decreasing from 98.83% → 97.18% (−1.65 pp). These results come with trade-offs: mapped models can train substantially slower, and performance…

热度 47.5 / 100；排名与评分保留该期记录。