Goto

Collaborating Authors

 theorem4


TowardtheFundamentalLimitsofImitation Learning

Neural Information Processing Systems

We then propose a novel algorithm based on minimum-distance functionals in the setting where the transition model is given and the expert is deterministic.Thealgorithmissuboptimalby .|S|H3/2/N,matchingourlower


How To Make the Gradients Small Stochastically: Even Faster Convex and Nonconvex SGD

Zeyuan Allen-Zhu

Neural Information Processing Systems

However, in terms of making the gradients small, the original SGD does not give an optimal rate, even when f(x) is convex. If f(x) is convex, to find a point with gradient norm ε, we design an algorithm SGD3withanear-optimalrate eO(ε 2),improvingthebestknownrateO(ε 8/3) of [17].


CategorizedBandits

Neural Information Processing Systems

In the multi-armed bandit problem, an agent has several possible decisions, usually referred to as "arms", and chooses or "pulls" sequentially one of them at each time step. This generates a sequence of rewards and the objective is to maximize their cumulative sum.




cdd0640218a27e9e2c0e52e324e25db0-Paper-Conference.pdf

Neural Information Processing Systems

The fair-ranking problem, which asks to rank a given set of items to maximize utility subject togroup fairness constraints, has received attention inthe fairness, information retrieval, and machine learning literature.




TowardsaUnified Information-Theoretic FrameworkforGeneralization

Neural Information Processing Systems

Let D be an unknown distribution on a spaceZ, and let H be a set of classifiers. Consider a (randomized) learning algorithmA = (An)n 1 that selects an elementˆh in H, based onn i.i.d.