Many learning algorithms rely on the curvature (in particular, strong convexity) of regularized objective functions to provide good theoretical performance guarantees. In practice...
Interconnect delay has become a critical factor in determining the performance of integrated circuits. Routing and buffering are powerful means of improving the circuit speed and ...
Abstract— We present a model for the joint design of congestion control and media access control (MAC) for ad hoc wireless networks. Using contention graph and contention matrix,...
With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...
We present novel semi-supervised boosting algorithms that incrementally build linear combinations of weak classifiers through generic functional gradient descent using both labele...