← Search

Forrest John Laine

2 accepted papers

2025

Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training

ICML 2025poster

In a neural network with ReLU activations, the number of piecewise linear regions in the output can grow exponentially with depth. However, this is highly unlikely to happen when the initial parameters are sampled randomly, which therefore often leads to the use of networks that are unnecessarily la…

Cited by 0SourcePDFScholar
2025

Online Competitive Information Gathering for Partially Observable Trajectory Games

RSS 2025poster

To cooperate or compete rationally in continuous, partially observable multi-agent spaces, game theoretic agents must make plans that optimally gather information about their opponents. These problems are modeled by partially observable stochastic games (POSGs), but planning in fully continuous POSG…

Cited by 0PDFScholar