Research
There is widespread sentiment that it is not possible to effectively utilize fast gradient methods (e.g. Nesterov’s acceleration, conjugate gradient, heavy ball) for the purposes of stochastic optimization due to their instability and error accumulation,…
Optimization methods are the engine of machine learning algorithms. Examples abound, such as training neural networks with stochastic gradient descent, segmenting images with submodular optimization, or efficiently searching a game tree with bandit algorithms. We…
Many real-world problems, such as network packet routing and the coordination of autonomous vehicles, are naturally modelled as cooperative multi-agent systems. In this talk, I overview some of the key challenges in developing reinforcement learning…
In this tutorial we discuss several recent advances in deep reinforcement learning involving policy gradient methods. These methods have shown significant success in a wide range of domains, including continuous-action domains such as manipulation, locomotion,…
Can higher-order functional programs solve more problems than first-order programs? Answer: NO, since both program classes are Turing complete. The reason is that higher-order values can be simulated by first-order values: use function “closures” built…
We consider the problem of estimating the value of MAX-CUT in a graph in the streaming model of computation. We show that there exists a constant $\e_* > 0$ such that any randomized streaming algorithm…
Consider a flying drone controlled from the ground by an observer who communicates with it via wireless. We are interested in how well the drone can be controlled via a channel that accepts r bits/sec.…
