搜索结果: 136-150 共查到“知识库 科学技术统计学”相关记录243条 . 查询时间(2.871 秒)
A Method for Comparing Hedge Funds
time-series classification signal analysis portfolio diversification search engines hedge funds
2013/4/28
The paper presents new machine learning methods: signal composition, which classifies time-series regardless of length, type, and quantity; and self-labeling, a supervised-learning enhancement. The pa...
We propose one-class support measure machines (OCSMMs) for group anomaly detection which aims at recognizing anomalous aggregate behaviors of data points. The OCSMMs generalize well-known one-class su...
Maximal Information Divergence from Statistical Models defined by Neural Networks
neural network exponential family Kullback-Leibler diver-gence multi-information
2013/4/27
We review recent results about the maximal values of the Kullback-Leibler information divergence from statistical models defined by neural networks, including naive Bayes models, restricted Boltzmann ...
Inter Time Series Sales Forecasting
Association mining Combining Decomposition Forecasting Inter time series.
2013/4/27
Combining forecast from different models has shown to perform better than single forecast in most time series. To improve the quality of forecast we can go for combining forecast. We study the effect ...
High-Frequency Tail Index Estimation by Nearly Tight Frames
High-Frequency Tail Index Estimation Nearly Tight Frames
2013/4/27
This work develops the asymptotic properties (weak consistency and Gaussianity), in the high-frequency limit, of approximate maximum likelihood estimators for the spectral parameters of Gaussian and i...
Bio-Signals-based Situation Comparison Approach to Predict Pain
Time-series classification signal analysis situation classification
2013/4/27
his paper describes a time-series-based classification approach to identify similarities between bio-medical-based situations. The proposed approach allows classifying collections of time-series repre...
Efficient Regularized Least-Squares Algorithms for Conditional Ranking on Relational Data
Efficient Regularized;Least-Squares;Algorithms;Conditional Ranking;Relational Data
2012/11/23
In domains like bioinformatics, information retrieval and social network analysis, one can find learning tasks where the goal consists of inferring a ranking of objects, conditioned on a particular ta...
Distribution of the largest eigenvalue for real Wishart and Gaussian random matrices and a simple approximation for the Tracy-Widom distribution
Random Matrix Theory characteristic roots largest eigenvalue Tracy-Widom Distribution Wishart Matrices Gaussian Orthogonal Ensemble
2012/11/23
We derive the exact distribution of the largest eigenvalue for finite dimensions real Wishart matrices and for the Gaussian Orthogonal Ensemble (GOE). We compare the exact distribution with the Tracy-...
Further Optimal Regret Bounds for Thompson Sampling
Further Optimal Regret Bounds Thompson Sampling
2012/11/23
Thompson Sampling is one of the oldest heuristics for multi-armed bandit problems. It is a randomized algorithm based on Bayesian ideas, and has recently generated significant interest after several s...
Thompson Sampling for Contextual Bandits with Linear Payoffs
Thompson Sampling Contextual Bandits Linear Payoffs
2012/11/23
Thompson Sampling is one of the oldest heuristics for multi-armed bandit problems. It is a randomized algorithm based on Bayesian ideas, and has recently generated significant interest after several s...
Minimax Multi-Task Learning and a Generalized Loss-Compositional Paradigm for MTL
Minimax Multi-Task Learning a Generalized Loss-Compositional Paradigm MTL
2012/11/23
Since its inception, the modus operandi of multi-task learning (MTL) has been to minimize the task-wise mean of the empirical risks. We introduce a generalized loss-compositional paradigm for MTL that...
We study algorithms for matching user tracks, consisting of time-ordered location points, to paths in the road network. Previous work has focused on the scenario where the location data is linearly or...
We consider the restless Markov bandit problem, in which the state of each arm evolves according to a Markov process independently of the learner's actions. We suggest an algorithm that after $T$ step...
NetSimile: A Scalable Approach to Size-Independent Network Similarity
NetSimile Scalable Approach Size-Independent Network Similarity
2012/11/23
Given a set of k networks, possibly with different sizes and no overlaps in nodes or edges, how can we quickly assess similarity between them, without solving the node-correspondence problem? Analogou...
On the Complexity of Bandit and Derivative-Free Stochastic Convex Optimization
Bandit Derivative-Free Stochastic Convex Optimization
2012/11/23
The problem of stochastic convex optimization with bandit feedback (in the learning community) or without knowledge of gradients (in the optimization community) has received much attention in recent y...