Introduction to algorithms
Machine Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence
Ridge Regression Learning Algorithm in Dual Variables
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
On the influence of the kernel on the consistency of support vector machines
The Journal of Machine Learning Research
Smooth minimization of non-smooth functions
Mathematical Programming: Series A and B
Adaptive language modeling using minimum discriminant estimation
HLT '91 Proceedings of the workshop on Speech and Natural Language
Smoothing Technique and its Applications in Semidefinite Optimization
Mathematical Programming: Series A and B
New analysis and algorithm for learning with drifting distributions
ALT'12 Proceedings of the 23rd international conference on Algorithmic Learning Theory
On the hardness of domain adaptation and the utility of unlabeled target samples
ALT'12 Proceedings of the 23rd international conference on Algorithmic Learning Theory
Domain adaptation and sample bias correction theory and algorithm for regression
Theoretical Computer Science
Hi-index | 0.00 |
This paper presents a series of new results for domain adaptation in the regression setting. We prove that the discrepancy is a distance for the squared loss when the hypothesis set is the reproducing kernel Hilbert space induced by a universal kernel such as the Gaussian kernel. We give new pointwise loss guarantees based on the discrepancy of the empirical source and target distributions for the general class of kernel-based regularization algorithms. These bounds have a simpler form than previous results and hold for a broader class of convex loss functions not necessarily differentiable, including Lq losses and the hinge loss. We extend the discrepancy minimization adaptation algorithm to the more significant case where kernels are used and show that the problem can be cast as an SDP similar to the one in the feature space. We also show that techniques from smooth optimization can be used to derive an efficient algorithm for solving such SDPs even for very high-dimensional feature spaces. We have implemented this algorithm and report the results of experiments demonstrating its benefits for adaptation and show that, unlike previous algorithms, it can scale to large data sets of tens of thousands or more points.