Sciweavers

Share
COLT
2010
Springer
9 years 1 months ago
Nonparametric Bandits with Covariates
We consider a bandit problem which involves sequential sampling from two populations (arms). Each arm produces a noisy reward realization which depends on an observable random cov...
Philippe Rigollet, Assaf Zeevi
COLT
2010
Springer
9 years 1 months ago
Convex Games in Banach Spaces
We study the regret of an online learner playing a multi-round game in a Banach space B against an adversary that plays a convex function at each round. We characterize the minima...
Karthik Sridharan, Ambuj Tewari
COLT
2010
Springer
9 years 1 months ago
Improved Guarantees for Agnostic Learning of Disjunctions
Pranjal Awasthi, Avrim Blum, Or Sheffet
COLT
2010
Springer
9 years 1 months ago
Inferring Descriptive Generalisations of Formal Languages
In the present paper, we introduce a variant of Gold-style learners that is not required to infer precise descriptions of the languages in a class, but that must find descriptive ...
Dominik D. Freydenberger, Daniel Reidenbach
COLT
2010
Springer
9 years 1 months ago
Following the Flattened Leader
We analyze the regret, measured in terms of log loss, of the maximum likelihood (ML) sequential prediction strategy. This "follow the leader" strategy also defines one o...
Wojciech Kotlowski, Peter Grünwald, Steven de...
COLT
2010
Springer
9 years 1 months ago
An Asymptotically Optimal Bandit Algorithm for Bounded Support Models
Multiarmed bandit problem is a typical example of a dilemma between exploration and exploitation in reinforcement learning. This problem is expressed as a model of a gambler playi...
Junya Honda, Akimichi Takemura
COLT
2010
Springer
9 years 1 months ago
Adaptive Subgradient Methods for Online Learning and Stochastic Optimization
We present a new family of subgradient methods that dynamically incorporate knowledge of the geometry of the data observed in earlier iterations to perform more informative gradie...
John Duchi, Elad Hazan, Yoram Singer
COLT
2010
Springer
9 years 1 months ago
Robust Hierarchical Clustering
One of the most widely used techniques for data clustering is agglomerative clustering. Such algorithms have been long used across many different fields ranging from computational...
Maria-Florina Balcan, Pramod Gupta
COLT
2010
Springer
9 years 1 months ago
Deterministic Sparse Fourier Approximation via Fooling Arithmetic Progressions
A significant Fourier transform (SFT) algorithm, given a threshold and oracle access to a function f, outputs (the frequencies and approximate values of) all the -significant Fou...
Adi Akavia
COLT
2010
Springer
9 years 1 months ago
Composite Objective Mirror Descent
We present a new method for regularized convex optimization and analyze it under both online and stochastic optimization settings. In addition to unifying previously known firstor...
John Duchi, Shai Shalev-Shwartz, Yoram Singer, Amb...
books