Search Results for author:
Found 26 papers, 5 papers with code
Faster solutions of the inverse pairwise Ising problem
Recent work has shown that probabilistic models based on pairwise interactions-in the simplest case, the Ising model-provide surprisingly accurate descriptions of experiments on real biological networks ranging from neurons to genes.
A Contextual-Bandit Approach to Personalized News Article Recommendation
In this work, we model personalized recommendation of news articles as a contextual bandit problem, a principled approach in which a learning algorithm sequentially selects articles to serve users based on contextual information about the users and articles, while simultaneously adapting its article-selection strategy based on user-click feedback to maximize total user clicks.
A Reduction from Apprenticeship Learning to Classification
We provide new theoretical results for apprenticeship learning, a variant of reinforcement learning in which the true reward function is unknown, and the goal is to perform well relative to an observed expert.
Non-Stochastic Bandit Slate Problems
We consider bandit problems, motivated by applications in online advertising and news story selection, in which the learner must repeatedly select a slate, that is, a subset of size s from K possible actions, and then receives rewards for just the selected actions.
Towards Minimax Online Learning with Unknown Time Horizon
We apply a minimax analysis, beginning with the fixed horizon case, and then moving on to two unknown-horizon settings, one that assumes the horizon is chosen randomly according to some known distribution, and the other which allows the adversary full control over the horizon.
Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits
We present a new algorithm for the contextual bandit learning problem, where the learner repeatedly takes one of $K$ actions in response to the observed context, and observes the reward only for that chosen action.
A Drifting-Games Analysis for Online Learning and Applications to Boosting
Different online learning settings (Hedge, multi-armed bandit problems and online convex optimization) are studied by converting into various kinds of drifting games.
Achieving All with No Parameters: Adaptive NormalHedge
We study the classic online learning problem of predicting with expert advice, and propose a truly parameter-free and adaptive algorithm that achieves several objectives simultaneously without using any prior information.
Contextual Dueling Bandits
The first of these algorithms achieves particularly low regret, even when data is adversarial, although its time and space requirements are linear in the size of the policy space.
Efficient and Parsimonious Agnostic Active Learning
We develop a new active learning algorithm for the streaming setting satisfying three important properties: 1) It provably works for any classifier representation and classification problem including those with severe noise.
Fast Convergence of Regularized Learning in Games
We show that natural classes of regularized learning algorithms with a form of recency bias achieve faster convergence rates to approximate efficiency and to coarse correlated equilibria in multiplayer normal form games.
Efficient Algorithms for Adversarial Contextual Learning
We provide the first oracle efficient sublinear regret algorithms for adversarial versions of the contextual bandit problem.
Unsupervised Domain Adaptation Using Approximate Label Matching
Domain adaptation addresses the problem created when training data is generated by a so-called source distribution, but test data is generated by a significantly different target distribution.
Exploratory Gradient Boosting for Reinforcement Learning in Complex Domains
We address both of these challenges with two complementary techniques: First, we develop a gradient-boosting style, non-parametric function approximator for learning on $Q$-function residuals.
Improved Regret Bounds for Oracle-Based Adversarial Contextual Bandits
We give an oracle-based algorithm for the adversarial contextual bandit problem, where either contexts are drawn i. i. d.
Contextual Decision Processes with Low Bellman Rank are PAC-Learnable
Our first contribution is a complexity measure, the Bellman rank, that we show enables tractable learning of near-optimal behavior in these processes and is naturally small for many well-studied reinforcement learning settings.
Oracle-Efficient Online Learning and Auction Design
We consider the design of computationally efficient online learning algorithms in an adversarial setting in which the learner has access to an offline optimization oracle.
Corralling a Band of Bandit Algorithms
We study the problem of combining multiple bandit algorithms (that is, online learning algorithms with partial feedback) with the goal of creating a master algorithm that performs almost as well as the best base algorithm if it were to be run on its own.
On Oracle-Efficient PAC RL with Rich Observations
We study the computational tractability of PAC reinforcement learning with rich observations.
Practical Contextual Bandits with Regression Oracles
A major challenge in contextual bandits is to design general-purpose algorithms that are both practically useful and theoretically well-founded.
Gradient descent follows the regularization path for general losses
Recent work across many machine learning disciplines has highlighted that standard descent methods, even without explicit regularization, do not merely minimize the training error, but also exhibit an implicit bias.
Bayesian decision-making under misspecified priors with applications to meta-learning
We prove that the expected reward accrued by Thompson sampling (TS) with a misspecified prior differs by at most $\tilde{\mathcal{O}}(H^2 \epsilon)$ from TS with a well specified prior, where $\epsilon$ is the total-variation distance between priors and $H$ is the learning horizon.
Multiclass Boosting and the Cost of Weak Learning
Here, we focus on an especially natural formulation in which the weak hypotheses are assumed to belong to an ''easy-to-learn'' base class, and the weak learner is an agnostic PAC learner for that class with respect to the standard classification loss.
Convex Analysis at Infinity: An Introduction to Astral Space
Not all convex functions on $\mathbb{R}^n$ have finite minimizers; some can only be minimized by a sequence as it heads to infinity.
Provably Sample-Efficient RL with Side Information about Latent Dynamics
We study reinforcement learning (RL) in settings where observations are high-dimensional, but where an RL agent has access to abstract knowledge about the structure of the state space, as is the case, for example, when a robot is tasked to go to a specific room in a building using observations from its own camera, while having access to the floor plan.
Provable Interactive Learning with Hindsight Instruction Feedback
We study interactive learning in a setting where the agent has to generate a response (e. g., an action or trajectory) given a context and an instruction.
