174 citations · 346 across the 34 of their papers we have counts for
9 papers · 1 filter
Learning the Linear Quadratic Regulator from Nonlinear Observations
Zakaria Mhammedi, Dylan J. Foster, Max Simchowitz +5
We introduce a new problem setting for continuous control called the LQR with Rich Observations, or RichLQR. In our setting, the environment is summarized by a low-dimensional cont…
Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective
Dylan J. Foster, Alexander Rakhlin, David Simchi-Levi +1
In the classical multi-armed bandit problem, instance-dependent algorithms attain improved performance on "easy" problems with a gap between the best and second-best arm. Are simil…
Tight Bounds on Minimax Regret under Logarithmic Loss via Self-Concordance
Blair Bilodeau, Dylan J. Foster, Daniel M. Roy
We consider the classical problem of sequential probability assignment under logarithmic loss while competing against an arbitrary, potentially nonparametric class of experts. We o…
Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations
Yossi Arjevani, Yair Carmon, John C. Duchi +3
We design an algorithm which finds an -approximate stationary point (with ) using stochastic gradient and Hessian-vector products, matching gua…
Open Problem: Model Selection for Contextual Bandits
Dylan J. Foster, Akshay Krishnamurthy, Haipeng Luo
In statistical learning, algorithms for model selection allow the learner to adapt to the complexity of the best hypothesis class in a sequence. We ask whether similar guarantees a…
Learning nonlinear dynamical systems from a single trajectory
Dylan J. Foster, Alexander Rakhlin, Tuhin Sarkar
We introduce algorithms for learning nonlinear dynamical systems of the form , where is a weight matrix, is a nonlinear link…