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.
Field
Machine learning theory, optimisation and reliability
This field studies why and how learning works: optimisers and schedules for deep networks, generalisation and phenomena such as double descent and grokking, robustness under distribution shift, uncertainty and calibration, continual learning and federated learning. Empirical claims are tested with controlled experiments on standard small and medium benchmarks, many seeds, equal tuning budgets and metrics chosen to isolate the studied effect.