Search Results for author:
Found 15 papers, 1 papers with code
Generalization Properties of Retrieval-based Models
The second class of retrieval-based approaches we explore learns a global model using kernel methods to directly map an input instance and retrieved examples to a prediction, without explicitly solving a local learning task.
No Regrets for Learning the Prior in Bandits
We propose ${\tt AdaTS}$, a Thompson sampling algorithm that adapts sequentially to bandit tasks that it interacts with.
Episodic Bandits with Stochastic Experts
The agent interacts with the environment over episodes, with each episode having different context distributions; this results in the `best expert' changing across episodes.
Combinatorial Blocking Bandits with Stochastic Delays
Recent work has considered natural variations of the multi-armed bandit problem, where the reward distribution of each arm is a special function of the time passed since its last pulling.
Beyond $\log^2(T)$ Regret for Decentralized Bandits in Matching Markets
We design decentralized algorithms for regret minimization in the two-sided matching market with one-sided bandit feedback that significantly improves upon the prior works (Liu et al. 2020a, 2020b, Sankararaman et al. 2020).
Recoverability Landscape of Tree Structured Markov Random Fields under Symmetric Noise
Furthermore, we present a polynomial time, sample efficient algorithm that recovers the exact tree when this is possible, or up to the unidentifiability as promised by our characterization, when full recoverability is impossible.
On Generalization of Adaptive Methods for Over-parameterized Linear Regression
In this paper, we aim to characterize the performance of adaptive methods in the over-parameterized linear regression setting.
Stochastic Linear Bandits with Protected Subspace
We study a variant of the stochastic linear bandit problem wherein we optimize a linear objective function but rewards are accrued only orthogonal to an unknown subspace (which we interpret as a \textit{protected space}) given only zero-order stochastic oracle access to both the objective itself and protected subspace.
Dominate or Delete: Decentralized Competing Bandits in Serial Dictatorship
Online learning in a two-sided matching market, with demand side agents continuously competing to be matched with supply side (arms), abstracts the complex interactions under partial information on matching platforms (e. g. UpWork, TaskRabbit).
Contextual Blocking Bandits
Assuming knowledge of the context distribution and the mean reward of each arm-context pair, we cast the problem as an online bipartite matching problem, where the right-vertices (contexts) arrive stochastically and the left-vertices (arms) are blocked for a finite number of rounds each time they are matched.
On Under-exploration in Bandits with Mean Bounds from Confounded Data
We study a variant of the multi-armed bandit problem where side information in the form of bounds on the mean of each arm is provided.
Blocking Bandits
We show that with prior knowledge of the rewards and delays of all the arms, the problem of optimizing cumulative reward does not admit any pseudo-polynomial time algorithm (in the number of arms) unless randomized exponential time hypothesis is false, by mapping to the PINWHEEL scheduling problem.
Learning Mixtures of Graphs from Epidemic Cascades
When the conditions are met, i. e., when the graphs are connected with at least three edges, we give an efficient algorithm for learning the weights of both graphs with optimal sample complexity (up to log factors).
Decentralization in Bitcoin and Ethereum Networks
Blockchain-based cryptocurrencies have demonstrated how to securely implement traditionally centralized systems, such as currencies, in a decentralized fashion.
Cryptography and Security
Effective Evaluation using Logged Bandit Feedback from Multiple Loggers
In this paper, we address the question of how to estimate the performance of a new target policy when we have log data from multiple historic policies.
