Sciweavers

COLT
2004
Springer
14 years 5 months ago
A Statistical Mechanics Analysis of Gram Matrix Eigenvalue Spectra
Abstract. The Gram matrix plays a central role in many kernel methods. Knowledge about the distribution of eigenvalues of the Gram matrix is useful for developing appropriate model...
David C. Hoyle, Magnus Rattray
COLT
2004
Springer
14 years 5 months ago
Performance Guarantees for Regularized Maximum Entropy Density Estimation
Abstract. We consider the problem of estimating an unknown probability distribution from samples using the principle of maximum entropy (maxent). To alleviate overfitting with a v...
Miroslav Dudík, Steven J. Phillips, Robert ...
COLT
2004
Springer
14 years 5 months ago
Concentration Bounds for Unigrams Language Model
Abstract. We show several PAC-style concentration bounds for learning unigrams language model. One interesting quantity is the probability of all words appearing exactly k times in...
Evgeny Drukh, Yishay Mansour
COLT
2004
Springer
14 years 5 months ago
Learning Classes of Probabilistic Automata
Abstract. Probabilistic finite automata (PFA) model stochastic languages, i.e. probability distributions over strings. Inferring PFA from stochastic data is an open field of rese...
François Denis, Yann Esposito
COLT
2004
Springer
14 years 5 months ago
An Inequality for Nearly Log-Concave Distributions with Applications to Learning
Abstract— We prove that given a nearly log-concave distribution, in any partition of the space to two well separated sets, the measure of the points that do not belong to these s...
Constantine Caramanis, Shie Mannor
COLT
2004
Springer
14 years 5 months ago
Polynomial Time Prediction Strategy with Almost Optimal Mistake Probability
We give the first polynomial time prediction strategy for any PAC-learnable class C that probabilistically predicts the target with mistake probability poly(log(t)) t = ˜O 1 t w...
Nader H. Bshouty
COLT
2004
Springer
14 years 5 months ago
Learning a Hidden Graph Using O(log n) Queries Per Edge
We consider the problem of learning a general graph using edge-detecting queries. In this model, the learner may query whether a set of vertices induces an edge of the hidden grap...
Dana Angluin, Jiang Chen
COLT
2004
Springer
14 years 5 months ago
Regularization and Semi-supervised Learning on Large Graphs
We consider the problem of labeling a partially labeled graph. This setting may arise in a number of situations from survey sampling to information retrieval to pattern recognition...
Mikhail Belkin, Irina Matveeva, Partha Niyogi
COLT
2004
Springer
14 years 5 months ago
Inferring Mixtures of Markov Chains
We define the problem of inferring a “mixture of Markov chains” based on observing a stream of interleaved outputs from these chains. We show a sharp characterization of the i...
Tugkan Batu, Sudipto Guha, Sampath Kannan