Ambuj Tewari

Suggest Changes
Nicolò Cesa-Bianchi85
Peter L. Bartlett76
Gábor Lugosi69
Shai Shalev-Shwartz66
Tong Zhang53
42Nicolò Cesa-Bianchi
33Francesco Orabona
31Karthik Sridharan
30Csaba Szepesvári
30Alexander Rakhlin

Filter Results:

  • Full text PDF available (100)

Publication Year

2002
2017
  • This year (6)
  • Last 5 years (55)
  • Last 10 years (92)

Publication Type

Co-author

Journals and Conferences

Data Set Used

Key Phrases

Method

Learn More
PAC Subset Selection in Stochastic Multi-armed Bandits
We consider the problem of selecting, from among the arms of a stochastic n-armed bandit, a subset of size m of those arms with the highest expected rewards, based on efficiently sampling the arms. This " subset selection " problem finds application in a variety of areas. In the authors' previous work (Kalyanakrishnan & Stone, 2010), this problem is framed… (More)
On the Consistency of Multiclass Classification Methods
Binary classification is a well studied special case of the classification problem. Statistical properties of binary classifiers, such as consistency, have been investigated in a variety of settings. Binary classification methods can be generalized in many ways to handle multiple classes. It turns out that one can lose consistency in generalizing a binary… (More)
Learning with Noisy Labels
In this paper, we theoretically study the problem of binary classification in the presence of random classification noise — the learner, instead of seeing the true labels , sees labels that have independently been flipped with some small probability. Moreover, random label noise is class-conditional — the flip probability depends on the class. We provide… (More)
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 first-order algorithms, such as the projected gradient method, mirror descent, and forward-backward splitting, our method yields new analysis and algorithms. We also derive specific… (More)
Stochastic Methods for l1-regularized Loss Minimization
We describe and analyze two stochastic methods for <i>l</i><sub>1</sub> regularized loss minimization problems, such as the Lasso. The first method updates the weight of a single feature at each iteration while the second method updates the entire weight vector but only uses a single training example at each iteration. In both methods, the choice of… (More)
On the Complexity of Linear Prediction: Risk Bounds, Margin Bounds, and Regularization
This work characterizes the generalization ability of algorithms whose predictions are linear in the input vector. To this end, we provide sharp bounds for Rademacher and Gaussian complexities of (constrained) linear classes, which directly lead to a number of generalization bounds. This derivation provides simplified proofs of a number of corollaries… (More)
Efficient bandit algorithms for online multiclass prediction
This paper introduces the Banditron, a variant of the Perceptron [Rosenblatt, 1958], for the multiclass bandit setting. The multiclass bandit setting models a wide range of practical supervised learning applications where the learner only receives partial feedback (referred to as "bandit" feedback, in the spirit of multi-armed bandit models) with respect to… (More)
Online Bandit Learning against an Adaptive Adversary: from Regret to Policy Regret
Online learning algorithms are designed to learn even when their input is generated by an adversary. The widely-accepted formal definition of an online algorithm's ability to learn is the game-theoretic notion of regret. We argue that the standard definition of regret becomes inadequate if the adversary is allowed to adapt to the online algorithm's actions.… (More)