Results 1  10
of
2,174
Deviation Bounds for Wavelet Shrinkage
, 2001
"... We analyse the wavelet shrinkage algorithm of Donoho and Johnstone in order to assess the quality of the reconstruction of a signal obtained from noisy samples. We prove deviation bounds for the maximum of the squares of the error, and for the average of the squares of the error, under the assumptio ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
We analyse the wavelet shrinkage algorithm of Donoho and Johnstone in order to assess the quality of the reconstruction of a signal obtained from noisy samples. We prove deviation bounds for the maximum of the squares of the error, and for the average of the squares of the error, under
Large Deviation Bounds for kdesigns
, 903
"... We present a technique for derandomising large deviation bounds of functions on the unitary group. We replace the Haar distribution with a pseudorandom distribution, a kdesign. kdesigns have the first k moments equal to those of the Haar distribution. The advantage of this is that (approximate) k ..."
Abstract

Cited by 5 (2 self)
 Add to MetaCart
We present a technique for derandomising large deviation bounds of functions on the unitary group. We replace the Haar distribution with a pseudorandom distribution, a kdesign. kdesigns have the first k moments equal to those of the Haar distribution. The advantage of this is that (approximate
LARGE DEVIATIONS BOUND FOR TEICHMÜLLER FLOW
, 2009
"... Large deviation rates are obtained for suspension flows over symbolic dynamical systems with a countable alphabet. The method is that of [1]. A corollary of the main results is a large deviation bound for the Teichmüller flow on the moduli space of abelian differentials, which extends earlier work ..."
Abstract
 Add to MetaCart
Large deviation rates are obtained for suspension flows over symbolic dynamical systems with a countable alphabet. The method is that of [1]. A corollary of the main results is a large deviation bound for the Teichmüller flow on the moduli space of abelian differentials, which extends earlier
Large deviation bounds for Markov chains
"... We study the fraction of time that a Markov chain spends in a given subset of states. We give an exponential bound on the probability that it exceeds its expectation by a constant factor. Our bound depends on the mixing properties of the chain, and is asymptotically optimal for a certain class of Ma ..."
Abstract

Cited by 11 (0 self)
 Add to MetaCart
We study the fraction of time that a Markov chain spends in a given subset of states. We give an exponential bound on the probability that it exceeds its expectation by a constant factor. Our bound depends on the mixing properties of the chain, and is asymptotically optimal for a certain class
Large Deviations Bounds for Empirical Processes
, 1999
"... VapnikChervonenkis bounds on speeds of convergence of empirical means to their expectations have been continuously improved over the years. The result obtained by M. Talagrand in 1994 [11] seems to provide the final word as far as universal bounds are concerned. However, for fixed families of under ..."
Abstract
 Add to MetaCart
VapnikChervonenkis bounds on speeds of convergence of empirical means to their expectations have been continuously improved over the years. The result obtained by M. Talagrand in 1994 [11] seems to provide the final word as far as universal bounds are concerned. However, for fixed families
Inference in Multilayer Networks via Large Deviation Bounds
 NIPS
, 1999
"... We study probabilistic inference in large, layered Bayesian networks represented as directed acyclic graphs. We show that the intractability of exact inference in such networks does not preclude their effective use. We give algorithms for approximate probabilistic inference that exploit averaging ph ..."
Abstract

Cited by 8 (1 self)
 Add to MetaCart
phenomena occurring at nodes with large numbers of parents. We show that these algorithms compute rigorous lower and upper bounds on marginal probabilities of interest, prove that these bounds become exact in the limit of large networks, and provide rates of convergence.
Deviations bounds and conditional principles for thin sets
, 2008
"... The aim of this paper is to use non asymptotic bounds for the probability of rare events in the Sanov theorem, in order to study the asymptotics in conditional limit theorems (Gibbs conditioning principle for thin sets). Applications to stochastic mechanics or calibration problems for diffusion pr ..."
Abstract

Cited by 5 (1 self)
 Add to MetaCart
The aim of this paper is to use non asymptotic bounds for the probability of rare events in the Sanov theorem, in order to study the asymptotics in conditional limit theorems (Gibbs conditioning principle for thin sets). Applications to stochastic mechanics or calibration problems for diffusion
Two nonregular extensions of the large deviation bound
 BSIS Technical Reports No.024, http://www.bsis.brain.riken.go.jp/BSISTR.html: eprint math.PR/0212076
, 2002
"... We formulate two types of extension of the large deviation theory initiated by Bahadur in a nonregular setting. One can be regarded as a bound of the point estimation, the other can be regarded as the limit of a bound of the interval estimation. Both coincide in the regular case, but do not necessa ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
We formulate two types of extension of the large deviation theory initiated by Bahadur in a nonregular setting. One can be regarded as a bound of the point estimation, the other can be regarded as the limit of a bound of the interval estimation. Both coincide in the regular case, but do
Large deviation bounds for the volume of the largest cluster
, 2013
"... Abstract. Let Mn denote the number of sites in the largest cluster in critical site percolation on the triangular lattice inside a box side length n. We give lower and upper bounds on the probability that Mn/EMn> x of the form exp(−Cx2/α1) for x ≥ 1 and large n with α1 = 5/48 and C> 0. Our re ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
Abstract. Let Mn denote the number of sites in the largest cluster in critical site percolation on the triangular lattice inside a box side length n. We give lower and upper bounds on the probability that Mn/EMn> x of the form exp(−Cx2/α1) for x ≥ 1 and large n with α1 = 5/48 and C> 0. Our
LARGE DEVIATIONS BOUND FOR LORENZLIKE ATTRACTORS
, 804
"... Abstract. We obtain a exponential large deviation upper bound for continuous observables on suspension semiflows over a nonuniformly expanding base transformation with nonflat singularities (or criticalities), where the roof function defining the suspension behaves like the logarithm of the distan ..."
Abstract
 Add to MetaCart
Abstract. We obtain a exponential large deviation upper bound for continuous observables on suspension semiflows over a nonuniformly expanding base transformation with nonflat singularities (or criticalities), where the roof function defining the suspension behaves like the logarithm
Results 1  10
of
2,174