Hash Kernels

نویسندگان

  • Qinfeng Shi
  • James Petterson
  • Gideon Dror
  • John Langford
  • Alexander J. Smola
  • Alexander L. Strehl
  • S. V. N. Vishwanathan
چکیده

We propose hashing to facilitate efficient kernels. This generalizes previous work using sampling and we show a principled way to compute the kernel matrix for data streams and sparse feature spaces. Moreover, we give deviation bounds from the exact kernel matrix. This has applications to estimation on strings and graphs.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Hash Kernels for Structured Data

We propose hashing to facilitate efficient kernels. This generalizes previous work using sampling and we show a principled way to compute the kernel matrix for data streams and sparse feature spaces. Moreover, we give deviation bounds from the exact kernel matrix. This has applications to estimation on strings and graphs.

متن کامل

Circulant Preconditioners Constructed From Kernels

We consider circulant preconditioners for Hermitian Toeplitz systems from the view point of function theory. We show that some well-known circulant preconditioners can be derived from convoluting the generating function f of the Toeplitz matrix with famous kernels like the Dirichlet and the Fej er kernels. Several circulant precondition-ers are then constructed using this approach. Finally, we ...

متن کامل

Toeplitz Operators and Weighted Bergman Kernels

For a smoothly bounded strictly pseudoconvex domain, we describe the boundary singularity of weighted Bergman kernels with respect to weights behaving like a power (possibly fractional) of a defining function, and, more generally, of the reproducing kernels of Sobolev spaces of holomorphic functions of any real order. This generalizes the classical result of Fefferman for the unweighted Bergman...

متن کامل

Min-Hash Fingerprints for Graph Kernels: A Trade-off among Accuracy, Efficiency, and Compression

Graph databases that emerge from several relevant scenarios (e.g., social networks, the Web) require powerful data management algorithms and techniques. A fundamental operation in graph data management is computing the similarity between two graphs. However, due to the large scale and high dimensionality of real graph databases, computing graph similarity becomes a challenging problem in real s...

متن کامل

An Improved Hash Function Based on the Tillich-Zémor Hash Function

Using the idea behind the Tillich-Zémor hash function, we propose a new hash function. Our hash function is parallelizable and its collision resistance is implied by a hardness assumption on a mathematical problem. Also, it is secure against the known attacks. It is the most secure variant of the Tillich-Zémor hash function until now.

متن کامل

The submission is for the special topic on Large Scale Learning Hash Kernels for Structured Data

We propose hashing to facilitate efficient kernels. This generalizes previous work using sampling and we show a principled way to compute the kernel matrix for data streams and sparse feature spaces. Moreover, we give deviation bounds from the exact kernel matrix. This has applications to estimation on strings and graphs.

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2009