JMLR 2024 papers on Architectures and efficiency
19 of the 391 papers published in JMLR 2024 (4.9%) are on Architectures and efficiency, compared with 2.8% at JMLR 2023. They fall into 4 topics.
See JMLR 2024 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
RNNs and normalization · 15 papers
- AMLB: an AutoML Benchmark (93 citations)
- How Two-Layer Neural Networks Learn, One (Giant) Step at a Time (73 citations)
- Random Fully Connected Neural Networks as Perturbatively Solvable Hierarchies (31 citations)
- A Rainbow in Deep Network Black Boxes (29 citations)
- Deep Network Approximation: Beyond ReLU to Diverse Activation Functions (20 citations)
- Simple Cycle Reservoirs are Universal (6 citations)
- Memory of recurrent networks: Do we compute it right? (4 citations)
- A tensor factorization model of multilayer network interdependence (3 citations)
- MLRegTest: A Benchmark for the Machine Learning of Regular Languages (3 citations)
- Memory-Efficient Sequential Pattern Mining with Hybrid Tries (2 citations)
- Commutative Scaling of Width and Depth in Deep Neural Networks
- Improving Lipschitz-Constrained Neural Networks by Learning Activation Functions
and 3 more in the interactive map.
