Results 11  20
of
72
The Forgetron: A kernelbased perceptron on a fixed budget
 In Advances in Neural Information Processing Systems 18
, 2005
"... The Perceptron algorithm, despite its simplicity, often performs well on online classification problems. The Perceptron becomes especially effective when it is used in conjunction with kernels. However, a common difficulty encountered when implementing kernelbased online algorithms is the amount of ..."
Abstract

Cited by 44 (5 self)
 Add to MetaCart
(Show Context)
The Perceptron algorithm, despite its simplicity, often performs well on online classification problems. The Perceptron becomes especially effective when it is used in conjunction with kernels. However, a common difficulty encountered when implementing kernelbased online algorithms is the amount of memory required to store the online hypothesis, which may grow unboundedly. In this paper we describe and analyze a new infrastructure for kernelbased learning with the Perceptron while adhering to a strict limit on the number of examples that can be stored. We first describe a template algorithm, called the Forgetron, for online learning on a fixed budget. We then provide specific algorithms and derive a unified mistake bound for all of them. To our knowledge, this is the first online learning paradigm which, on one hand, maintains a strict limit on the number of examples it can store and, on the other hand, entertains a relative mistake bound. We also present experiments with real datasets which underscore the merits of our approach. 1
Efficient bandit algorithms for online multiclass prediction
 ICML, volume 307 of ACM International Conference Proceeding Series
, 2008
"... 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 ” feedba ..."
Abstract

Cited by 43 (5 self)
 Add to MetaCart
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 multiarmed bandit models) with respect to the true label (e.g. in many web applications users often only provide positive “click ” feedback which does not necessarily fully disclose a true label). The Banditron has the ability to learn in a multiclass classification setting with the “bandit ” feedback which only reveals whether or not the prediction made by the algorithm was correct or not (but does not necessarily reveal the true label). We provide (relative) mistake bounds which show how the Banditron enjoys favorable performance, and our experiments demonstrate the practicality of the algorithm. Furthermore, this paper pays close attention to the important special case when the data is linearly separable — a problem which has been exhaustively studied in the full information setting yet is novel in the bandit setting. 1.
Convex repeated games and Fenchel duality
 Advances in Neural Information Processing Systems 19
, 2006
"... We describe an algorithmic framework for an abstract game which we term a convex repeated game. We show that various online learning and boosting algorithms can be all derived as special cases of our algorithmic framework. This unified view explains the properties of existing algorithms and also ena ..."
Abstract

Cited by 39 (8 self)
 Add to MetaCart
(Show Context)
We describe an algorithmic framework for an abstract game which we term a convex repeated game. We show that various online learning and boosting algorithms can be all derived as special cases of our algorithmic framework. This unified view explains the properties of existing algorithms and also enables us to derive several new interesting algorithms. Our algorithmic framework stems from a connection that we build between the notions of regret in game theory and weak duality in convex optimization. 1
Mind the Duality Gap: Logarithmic regret algorithms for online optimization
"... We describe a primaldual framework for the design and analysis of online strongly convex optimization algorithms. Our framework yields the tightest known logarithmic regret bounds for FollowTheLeader and for the gradient descent algorithm proposed in Hazan et al. [2006]. We then show that one can ..."
Abstract

Cited by 35 (0 self)
 Add to MetaCart
(Show Context)
We describe a primaldual framework for the design and analysis of online strongly convex optimization algorithms. Our framework yields the tightest known logarithmic regret bounds for FollowTheLeader and for the gradient descent algorithm proposed in Hazan et al. [2006]. We then show that one can interpolate between these two extreme cases. In particular, we derive a new algorithm that shares the computational simplicity of gradient descent but achieves lower regret in many practical situations. Finally, we further extend our framework for generalized strongly convex functions. 1
On the Generalization Ability of Online Strongly Convex Programming Algorithms
"... This paper examines the generalization properties of online convex programming algorithms when the loss function is Lipschitz and strongly convex. Our main result is a sharp bound, that holds with high probability, on the excess risk of the output of an online algorithm in terms of the average regre ..."
Abstract

Cited by 35 (2 self)
 Add to MetaCart
(Show Context)
This paper examines the generalization properties of online convex programming algorithms when the loss function is Lipschitz and strongly convex. Our main result is a sharp bound, that holds with high probability, on the excess risk of the output of an online algorithm in terms of the average regret. This allows one to use recent algorithms with logarithmic cumulative regret guarantees to achieve fast convergence rates for the excess risk with high probability. As a corollary, we characterize the convergence rate of PEGASOS (with high probability), a recently proposed method for solving the SVM optimization problem. 1
Noise tolerant variants of the perceptron algorithm
 Journal of Machine Learning Research
, 2005
"... A large number of variants of the Perceptron algorithm have been proposed and partially evaluated in recent work. One type of algorithm aims for noise tolerance by replacing the last hypothesis of the perceptron with another hypothesis or a vote among hypotheses. Another type simply adds a margin te ..."
Abstract

Cited by 33 (2 self)
 Add to MetaCart
A large number of variants of the Perceptron algorithm have been proposed and partially evaluated in recent work. One type of algorithm aims for noise tolerance by replacing the last hypothesis of the perceptron with another hypothesis or a vote among hypotheses. Another type simply adds a margin term to the perceptron in order to increase robustness and accuracy, as done in support vector machines. A third type borrows further from support vector machines and constrains the update function of the perceptron in ways that mimic softmargin techniques. The performance of these algorithms, and the potential for combining different techniques, has not been studied in depth. This paper provides such an experimental study and reveals some interesting facts about the algorithms. In particular the perceptron with margin is an effective method for tolerating noise and stabilizing the algorithm. This is surprising since the margin in itself is not designed or used for noise tolerance, and there are no known guarantees for such performance. In most cases, similar performance is obtained by the votedperceptron which has the advantage that it does not require parameter selection. Techniques using soft margin ideas are runtime intensive and do not give additional performance benefits. The results also highlight the difficulty with automatic parameter selection which is required with some of these variants.
A PrimalDual Perspective of Online Learning Algorithms
"... We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a subfamily of universal online bounds as an optimization problem. Using the weak duality theorem we reduce the process of online learning to ..."
Abstract

Cited by 32 (7 self)
 Add to MetaCart
We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a subfamily of universal online bounds as an optimization problem. Using the weak duality theorem we reduce the process of online learning to the task of incrementally increasing the dual objective function. The amount by which the dual increases serves as a new and natural notion of progress for analyzing online learning algorithms. We are thus able to tie the primal objective value and the number of prediction mistakes using the increase in the dual.
Discriminative keyword spotting
 In Proc. of Workshop on NonLinear Speech Processsing
, 2007
"... This paper proposes a new approach for keyword spotting, which is not based on HMMs. The proposed method employs a new discriminative learning procedure, in which the learning phase aims at maximizing the area under the ROC curve, ..."
Abstract

Cited by 25 (10 self)
 Add to MetaCart
(Show Context)
This paper proposes a new approach for keyword spotting, which is not based on HMMs. The proposed method employs a new discriminative learning procedure, in which the learning phase aims at maximizing the area under the ROC curve,
Online algorithm for hierarchical phoneme classification
 in Workshop on Multimodal Interaction and Related Machine Learning Algorithms; Lecture Notes in Computer Science
, 2004
"... Abstract. We present an algorithmic framework for phoneme classification where the set of phonemes is organized in a predefined hierarchical structure. This structure is encoded via a rooted tree which induces a metric over the set of phonemes. Our approach combines techniques from large margin kern ..."
Abstract

Cited by 24 (11 self)
 Add to MetaCart
(Show Context)
Abstract. We present an algorithmic framework for phoneme classification where the set of phonemes is organized in a predefined hierarchical structure. This structure is encoded via a rooted tree which induces a metric over the set of phonemes. Our approach combines techniques from large margin kernel methods and Bayesian analysis. Extending the notion of large margin to hierarchical classification, we associate a prototype with each individual phoneme and with each phonetic group which corresponds to a node in the tree. We then formulate the learning task as an optimization problem with margin constraints over the phoneme set. In the spirit of Bayesian methods, we impose similarity requirements between the prototypes corresponding to adjacent phonemes in the phonetic hierarchy. We describe a new online algorithm for solving the hierarchical classification problem and provide worstcase loss analysis for the algorithm. We demonstrate the merits of our approach by applying the algorithm to synthetic data and as well as speech data. 1
Online learning meets optimization in the dual
 In COLT
, 2006
"... Abstract. We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a subfamily of universal online bounds as an optimization problem. Using the weak duality theorem we reduce the process of online lea ..."
Abstract

Cited by 23 (5 self)
 Add to MetaCart
(Show Context)
Abstract. We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a subfamily of universal online bounds as an optimization problem. Using the weak duality theorem we reduce the process of online learning to the task of incrementally increasing the dual objective function. The amount by which the dual increases serves as a new and natural notion of progress. We are thus able to tie the primal objective value and the number of prediction mistakes using and the increase in the dual. The end result is a general framework for designing and analyzing old and new online learning algorithms in the mistake bound model. 1