Jason D. Lee
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1Stats ML×1
Frequent co-authors
Research Timeline
2026
Algorithmic Separation between Constant-Depth and Logarithmic-Depth Neural Networks
This paper provides the first algorithmic separation between constant-depth and logarithmic-depth networks, identifying a class of Boolean functions that logarithmic-depth networks can learn efficiently and exhibiting a subclass for which constant-depth networks incur constant approximation error.
Highlighted terms show continued research focus across papers