Fields
Pick a domain and keep going deeper: field, subfield, topic. Every step lists the papers at that point or below it. The counts are papers that are accepted or in review; papers that were not accepted are in the full library.
Subfield
Optimisation for deep learning (optimisers and schedules)
Benchmarks: AlgoPerf, DeepOBS, Crowded-valley optimizer benchmark, CIFAR-10 speedruns (airbench) and others. Datasets: CIFAR-10 / CIFAR-100, ImageNet-1k, WikiText-103, Tiny Shakespeare (nanoGPT) and others. Baselines: SGD with momentum, Adam, AdamW, Cosine schedule with warm restarts and others.