
Independent Policy Gradient Methods for Competitive Reinforcement Learning
We obtain global, nonasymptotic convergence guarantees for independent ...
read it

Learning the Linear Quadratic Regulator from Nonlinear Observations
We introduce a new problem setting for continuous control called the LQR...
read it

InstanceDependent Complexity of Contextual Bandits and Reinforcement Learning: A DisagreementBased Perspective
In the classical multiarmed bandit problem, instancedependent algorith...
read it

Improved Bounds on Minimax Regret under Logarithmic Loss via SelfConcordance
We consider the classical problem of sequential probability assignment u...
read it

SecondOrder Information in NonConvex Stochastic Optimization: Power and Limitations
We design an algorithm which finds an ϵapproximate stationary point (wi...
read it

Open Problem: Model Selection for Contextual Bandits
In statistical learning, algorithms for model selection allow the learne...
read it

Learning nonlinear dynamical systems from a single trajectory
We introduce algorithms for learning nonlinear dynamical systems of the ...
read it

Logarithmic Regret for Adversarial Online Control
We introduce a new algorithm for online linearquadratic control in a kn...
read it

Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles
A fundamental challenge in contextual bandits is to develop flexible, ge...
read it

Naive Exploration is Optimal for Online LQR
We consider the problem of online adaptive control of the linear quadrat...
read it

Lower Bounds for NonConvex Stochastic Optimization
We lower bound the complexity of finding ϵstationary points (with gradi...
read it

ℓ_∞ Vector Contraction for Rademacher Complexity
We show that the Rademacher complexity of any R^Kvalued function class ...
read it

Model selection for contextual bandits
We introduce the problem of model selection for contextual bandits, wher...
read it

Sumofsquares meets square loss: Fast rates for agnostic tensor completion
We study tensor completion in the agnostic setting. In the classical ten...
read it

Hypothesis Set Stability and Generalization
We present an extensive study of generalization for datadependent hypot...
read it

Distributed Learning with Sublinear Communication
In distributed statistical learning, N samples are split across m machin...
read it

Orthogonal Statistical Learning
We provide excess risk guarantees for statistical learning in the presen...
read it

Uniform Convergence of Gradients for NonConvex Learning and Optimization
We investigate 1) the rate at which refined properties of the empirical ...
read it

Contextual bandits with surrogate losses: Margin bounds and efficient algorithms
We introduce a new family of marginbased regret guarantees for adversar...
read it

Logistic Regression: The Importance of Being Improper
Learning linear predictors with the logistic lossboth in stochastic a...
read it

Online Learning: Sufficient Statistics and the Burkholder Method
We uncover a fairly general principle in online learning: If regret can ...
read it

Practical Contextual Bandits with Regression Oracles
A major challenge in contextual bandits is to design generalpurpose alg...
read it

Parameterfree online learning via model selection
We introduce an efficient algorithmic framework for model selection in o...
read it

Spectrallynormalized margin bounds for neural networks
This paper presents a marginbased multiclass generalization bound for n...
read it

ZigZag: A new approach to adaptive online learning
We develop a novel family of algorithms for the online learning setting ...
read it

Adaptive Online Learning
We propose a general framework for studying adaptive regret bounds in th...
read it
Dylan J. Foster
is this you? claim profile