Quasi-optimal range searching in spaces of finite VC-dimension
Discrete & Computational Geometry - Selected papers from the fourth ACM symposium on computational geometry, Univ. of Illinois, Urbana-Champaign, June 6 8, 1988
COLT '89 Proceedings of the second annual workshop on Computational learning theory
Approximations and optimal geometric divide-and-conquer
STOC '91 Proceedings of the twenty-third annual ACM symposium on Theory of computing
SIAM Journal on Scientific and Statistical Computing
Efficient distribution-free learning of probabilistic concepts
Journal of Computer and System Sciences - Special issue: 31st IEEE conference on foundations of computer science, Oct. 22–24, 1990
Sphere packing numbers for subsets of the Boolean n-cube with bounded Vapnik-Chervonenkis dimension
Journal of Combinatorial Theory Series A
Fat-shattering and the learnability of real-valued functions
Journal of Computer and System Sciences
On linear-time deterministic algorithms for optimization problems in fixed dimension
Journal of Algorithms
Scale-sensitive dimensions, uniform convergence, and learnability
Journal of the ACM (JACM)
Improved bounds on the sample complexity of learning
Journal of Computer and System Sciences
Improved Fast Gauss Transform and Efficient Kernel Density Estimation
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Range counting over multidimensional data streams
SCG '04 Proceedings of the twentieth annual symposium on Computational geometry
Near-Optimal Hashing Algorithms for Approximate Nearest Neighbor in High Dimensions
FOCS '06 Proceedings of the 47th Annual IEEE Symposium on Foundations of Computer Science
Matching point sets with respect to the Earth Mover's Distance
Computational Geometry: Theory and Applications
Earth mover distance over high-dimensional spaces
Proceedings of the nineteenth annual ACM-SIAM symposium on Discrete algorithms
Fast algorithms for the all nearest neighbors problem
SFCS '83 Proceedings of the 24th Annual Symposium on Foundations of Computer Science
A Hilbert Space Embedding for Distributions
ALT '07 Proceedings of the 18th international conference on Algorithmic Learning Theory
Algorithms for ε-Approximations of Terrains
ICALP '08 Proceedings of the 35th international colloquium on Automata, Languages and Programming, Part I
Sparse Approximation of Currents for Statistics on Curves and Surfaces
MICCAI '08 Proceedings of the 11th International Conference on Medical Image Computing and Computer-Assisted Intervention, Part II
Efficient Sketches for Earth-Mover Distance, with Applications
FOCS '09 Proceedings of the 2009 50th Annual IEEE Symposium on Foundations of Computer Science
Hilbert Space Embeddings and Metrics on Probability Measures
The Journal of Machine Learning Research
Constructive Algorithms for Discrepancy Minimization
FOCS '10 Proceedings of the 2010 IEEE 51st Annual Symposium on Foundations of Computer Science
IPMI'05 Proceedings of the 19th international conference on Information Processing in Medical Imaging
Tight hardness results for minimizing discrepancy
Proceedings of the twenty-second annual ACM-SIAM symposium on Discrete Algorithms
Image segmentation based on k-means clustering and energy-transfer proximity
ISVC'11 Proceedings of the 7th international conference on Advances in visual computing - Volume Part II
Radio tomographic imaging and tracking of stationary and moving people via kernel distance
Proceedings of the 12th international conference on Information processing in sensor networks
Quality and efficiency for kernel density estimates in large data
Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data
Moving heaven and earth: distances between distributions
ACM SIGACT News
Hi-index | 0.00 |
Starting with a similarity function between objects, it is possible to define a distance metric (the kernel distance) on pairs of objects, and more generally on probability distributions over them. These distance metrics have a deep basis in functional analysis and geometric measure theory, and have a rich structure that includes an isometric embedding into a Hilbert space. They have recently been applied to numerous problems in machine learning and shape analysis. SIn this paper, we provide the first algorithmic analysis of these distance metrics. Our main contributions are as follows: We present fast approximation algorithms for computing the kernel distance between two point sets P and Q that runs in near-linear time in the size of P ∪ Q (an explicit calculation would take quadratic time). We present polynomial-time algorithms for approximately minimizing the kernel distance under rigid transformation; they run in time O(n + poly(1/ε, log n)). We provide several general techniques for reducing complex objects to convenient sparse representations (specifically to point sets or sets of points sets) which approximately preserve the kernel distance. In particular, this allows us to reduce problems of computing the kernel distance between various types of objects such as curves, surfaces, and distributions to computing the kernel distance between point sets.