icml 2005 论文列表
Machine Learning, Proceedings of the Twenty-Second International Conference (ICML 2005), Bonn, Germany, August 7-11, 2005.
|
Large margin non-linear embedding.
Harmonic mixtures: combining mixture models and graph-based methods for inductive and scalable semi-supervised learning.
2D Conditional Random Fields for Web information extraction.
Learning from labeled and unlabeled data on a directed graph.
A new Mallows distance based metric for comparing clusterings.
Augmenting naive Bayes for ranking.
Learning Gaussian processes from multiple tasks.
Dirichlet enhanced relational learning.
Building Sparse Large Margin Classifiers.
Linear Asymmetric Classifier for cascade detectors.
Learning predictive state representations in dynamical systems without reset.
Incomplete-data classification using logistic regression.
Learning predictive representations from a history.
Bayesian sparse sampling for on-line reward optimization.
Exploiting syntactic, semantic and lexical regularities in language modeling via directed Markov random fields.
New kernels for protein structural motif discovery and function classification.
Implicit surface modelling as an eigenvalue problem.
Hierarchical Dirichlet model for document classification.
Propagating distributions on a hypergraph by dual information regularization.
Core Vector Regression for very large regression problems.
Learning discontinuities with products-of-sigmoids for switching between local models.
Learning structured prediction models: a large margin approach.
TD(lambda) networks: temporal-difference networks with eligibility traces.
Finite time bounds for sampling based fitted value iteration.
Unifying the error-correcting and output-code AdaBoost within the margin framework.
Explanation-Augmented SVM: an approach to incorporating domain knowledge into SVM learning.
A theoretical analysis of Model-Based Interval Estimation.
Large scale genomic sequence SVM classifiers.
Compact approximations to Bayesian predictive distributions.
Active learning for sampling in time-series experiments with application to gene expression analysis.
Beyond the point cloud: from transductive to semi-supervised learning.
Identifying useful subgoals in reinforcement learning by local graph partitioning.
New d-separation identification results for learning continuous latent variable models.
Fast inference and learning in large-state-space HMMs.
Non-negative tensor factorization with applications to statistics and computer vision.
Analysis and extension of spectral methods for nonlinear dimensionality reduction.
Object correspondence as a machine learning problem.
Supervised dimensionality reduction using mixture models.
Estimating and computing density based distance metrics.
Expectation maximization algorithms for conditional likelihoods.
Learning hierarchical multi-category text classification models.
Integer linear programming inference for conditional random fields.
Why skewing works: learning difficult Boolean functions with greedy tree learners.
Coarticulation: an approach for generating concurrent plans in Markov decision processes.
Fast maximum margin matrix factorization for collaborative prediction.
Generalized skewing for functions with continuous and nominal attributes.
Supervised versus multiple instance learning: an empirical comparison.
Healing the relevance vector machine through augmentation.
A model for handling approximate, noisy or incomplete labeling in text classification.
Independent subspace analysis using geodesic spanning trees.
Optimizing abstaining classifiers using ROC analysis.
Discriminative versus generative parameter and structure learning of Bayesian network classifiers.
Q-learning of sequential attention for visual object recognition from informative local descriptors.
A graphical model for chord progressions embedded in a psychoacoustic space.
Recycling data for multi-agent learning.
Predicting good probabilities with supervised learning.
An efficient method for simplifying support vector machines.
Learning first-order probabilistic models with combining rules.
Dynamic preferences in multi-criteria reinforcement learning.
High speed obstacle avoidance using monocular vision and reinforcement learning.
Weighted decomposition kernels.
Comparing clusterings: an axiomatic view.
Bounded real-time dynamic programming: RTDP with monotone upper bounds and performance guarantees.
The cross entropy method for classification.
Proto-value functions: developmental reinforcement learning.
Modeling word burstiness using the Dirichlet distribution.
ROC confidence bands: an empirical evaluation.
Naive Bayes models for probability estimation.
Unsupervised evidence integration.
Predicting protein folds with structural repeats using a chain graph model.
Logistic regression with an auxiliary data source.
Predicting relative performance of classifiers from samples.
Heteroscedastic Gaussian process regression.
PAC-Bayes risk bounds for sample-compressed Gibbs classifiers.
Relating reinforcement learning performance to classification performance.
A brain computer interface with online feedback based on magnetoencephalography.
Semi-supervised graph clustering: a kernel approach.
Using additive expert ensembles to cope with concept drift.
Learning the structure of Markov logic networks.
Computational aspects of Bayesian partition models.
Ensembles of biased classifiers.
Generalized LARS as an effective feature selection tool for text classification with SVMs.
A comparison of tight generalization error bounds.
A causal approach to hierarchical decomposition of factored MDPs.
Interactive learning of mappings from visual percepts to actions.
Error bounds for correlation clustering.
A support vector method for multivariate performance measures.
Efficient discriminative learning of Bayesian network classifier via boosted augmented naive Bayes.
A smoothed boosting algorithm using probabilistic output codes.
Learn to weight terms in information retrieval using category information.
Evaluating machine learning for information extraction.
Learning approximate preconditions for methods in hierarchical plans.
Multi-class protein fold recognition using adaptive codes.
A martingale framework for concept change detection in time-varying data streams.
Adapting two-class support vector classification methods to many class problems.
Online learning over graphs.
Bayesian hierarchical clustering.
Intrinsic dimensionality estimation of submanifolds in Rd.
Statistical and computational analysis of locality preserving projection.
Robust one-class clustering using hybrid global and local search.
Near-optimal sensor placements in Gaussian processes.
Learning strategies for story comprehension: a reinforcement learning approach.
Online feature selection for pixel classification.
Hierarchic Bayesian models for kernel learning.
Closed-form dual perturb and combine for tree-based models.
Optimal assignment kernels for attributed molecular graphs.
Supervised clustering with support vector machines.
Experimental comparison between bagging and Monte Carlo ensemble classification.
Reinforcement learning with Gaussian processes.
Combining model-based and instance-based learning for first order regression.
A practical generalization of Fourier-based learning.
Multimodal oriented discriminant analysis.
Learning as search optimization: approximate large margin methods for structured prediction.
Learning to compete, compromise, and cooperate in repeated general-sum games.
A general regression technique for learning transductions.
New approaches to support vector ordinal regression.
Preference learning with Gaussian processes.
Variational Bayesian image modelling.
Hedged learning: regret-minimization with learning experts.
Predicting probability distributions for surf height using an ensemble of mixture density networks.
Recognition and reproduction of gestures using a probabilistic framework combining PCA, ICA and HMM.
Learning class-discriminative dynamic Bayesian networks.
Learning to rank using gradient descent.
Reducing overfitting in process model induction.
Clustering through ranking on manifolds.
Action respecting embedding.
Multi-instance tree learning.
Error limiting reductions between classification tasks.
Multi-way distributional clustering via pairwise interactions.
Predictive low-rank decomposition for kernel methods.
Fast condensed nearest neighbor rule.
Tempering for Bayesian C&RT.
Active learning for Hidden Markov Models: objective functions and algorithms.
Exploration and apprenticeship learning in reinforcement learning.
