#### Filter Results:

- Full text PDF available (41)

#### Publication Year

1999

2014

- This year (0)
- Last 5 years (3)
- Last 10 years (14)

#### Publication Type

#### Co-author

#### Journals and Conferences

Learn More

- Vladimir Koltchinskii, Chaouki T. Abdallah, Marco Ariola, Peter Dorato, Dmitry Panchenko
- IEEE Trans. Automat. Contr.
- 2000

Recently, probabilistic methods and statistical learning theory have been shown to provide approximate solutions to “difficult” control problems. Unfortunately, the number of samples required in order to guarantee stringent performance levels may be prohibitively large. This paper introduces bootstrap learning methods and the concept of stopping times to… (More)

- Dmitry Panchenko
- 2003

We introduce a symmetrization technique that allows us to translate a problem of controlling the deviation of some functionals on a product space from their mean into a problem of controlling the deviation between two independent copies of the functional. As an application we give a new easy proof of Talagrand’s concentration inequality for empirical… (More)

In an important recent paper, [2], S. Franz and M. Leone prove rigorous lower bounds for the free energy of the diluted p-spin model and the K-sat model at any temperature. We show that the results for these two models are consequences of a single general principle. Our calculations are significantly simpler than those of [2], even in the replica-symmetric… (More)

In this paper we focus on the problem of estimating a bounded density using a finite combination of densities from a given class. We consider the Maximum Likelihood Procedure (MLE) and the greedy procedure described by Li and Barron [6, 7]. Approximation and estimation bounds are given for the above methods. We extend and improve upon the estimation results… (More)

- Dmitry Panchenko
- 2005

In [10] Michel Talagrand gave a rigorous proof of the Parisi formula in the SherringtonKirkpatrick model. In this paper we build upon the methodology developed in [10] and extend Talagrand’s result to a more general class of mean field models with spins distributed according to an arbitrary probability measure on the bounded subset of the real line and with… (More)

We conjecture that the Parisi functional in the Sherrington-Kirkpatrick model is convex in the functional order parameter. We prove a partial result that shows the convexity along “one-sided” directions. An interesting consequence of this result is the log-convexity of Lm norm for a class of random variables. 1 A problem and some results. Let M be a set of… (More)

- Dmitry Panchenko
- 2007

In order to study certain questions concerning the distribution of the overlap in Sherrington–Kirkpatrick type models, such as the chaos and ultrametricity problems, it seems natural to study the free energy of multiple systems with constrained overlaps. One can write analogues of Guerra's replica symmetry breaking bound for such systems but it is not at… (More)

- Polina Golland, Feng Liang, Sayan Mukherjee, Dmitry Panchenko
- COLT
- 2005

We introduce and explore an approach to estimating statistical significance of classification accuracy, which is particularly useful in scientific applications of machine learning where high dimensionality of the data and the small number of training examples render most standard convergence bounds too loose to yield a meaningful guarantee of the… (More)

We introduce and study several measures of complexity of functions from the convex hull of a given base class. These complexity measures take into account the sparsity of the weights of a convex combination as well as certain clustering properties of the base functions involved in it. We prove new upper confidence bounds on generalization error of ensemble… (More)