4 papers
On the Limited Representational Power of Value Functions and its Links to Statistical (In)Efficiency
David Cheikhi, Daniel Russo
Identifying the trade-offs between model-based and model-free methods is a central question in reinforcement learning. Value-based methods offer substantial computational advantage…
On the Statistical Benefits of Temporal Difference Learning
David Cheikhi, Daniel Russo
Given a dataset on actions and resulting long-term rewards, a direct estimation approach fits value functions that minimize prediction error on the training data. Temporal differen…
From Average Embeddings To Nearest Neighbor Search
Alexandr Andoni, David Cheikhi
In this note, we show that one can use average embeddings, introduced recently in [Naor'20, arXiv:1905.01280], to obtain efficient algorithms for approximate nearest neighbor searc…
Stochastic Flows and Geometric Optimization on the Orthogonal Group
Krzysztof Choromanski, David Cheikhi, Jared Davis +12
We present a new class of stochastic, geometrically-driven optimization algorithms on the orthogonal group and naturally reductive homogeneous manifolds obtained from the ac…