ترغب بنشر مسار تعليمي؟ اضغط هنا

Linear Classifiers in Product Space Forms

157   0   0.0 ( 0 )
 نشر من قبل Puoya Tabaghi
 تاريخ النشر 2021
والبحث باللغة English




اسأل ChatGPT حول البحث

Embedding methods for product spaces are powerful techniques for low-distortion and low-dimensional representation of complex data structures. Nevertheless, little is known regarding downstream learning and optimization problems in such spaces. Here, we address the problem of linear classification in a product space form -- a mix of Euclidean, spherical, and hyperbolic spaces. First, we describe new formulations for linear classifiers on a Riemannian manifold using geodesics and Riemannian metrics which generalize straight lines and inner products in vector spaces, respectively. Second, we prove that linear classifiers in $d$-dimensional space forms of any curvature have the same expressive power, i.e., they can shatter exactly $d+1$ points. Third, we formalize linear classifiers in product space forms, describe the first corresponding perceptron and SVM classification algorithms, and establish rigorous convergence results for the former. We support our theoretical findings with simulation results on several datasets, including synthetic data, CIFAR-100, MNIST, Omniglot, and single-cell RNA sequencing data. The results show that learning methods applied to small-dimensional embeddings in product space forms outperform their algorithmic counterparts in each space form.



قيم البحث

اقرأ أيضاً

We consider a discriminative learning (regression) problem, whereby the regression function is a convex combination of k linear classifiers. Existing approaches are based on the EM algorithm, or similar techniques, without provable guarantees. We dev elop a simple method based on spectral techniques and a `mirroring trick, that discovers the subspace spanned by the classifiers parameter vectors. Under a probabilistic assumption on the feature vector distribution, we prove that this approach has nearly optimal statistical efficiency.
Conditional generative models enjoy remarkable progress over the past few years. One of the popular conditional models is Auxiliary Classifier GAN (AC-GAN), which generates highly discriminative images by extending the loss function of GAN with an au xiliary classifier. However, the diversity of the generated samples by AC-GAN tends to decrease as the number of classes increases, hence limiting its power on large-scale data. In this paper, we identify the source of the low diversity issue theoretically and propose a practical solution to solve the problem. We show that the auxiliary classifier in AC-GAN imposes perfect separability, which is disadvantageous when the supports of the class distributions have significant overlap. To address the issue, we propose Twin Auxiliary Classifiers Generative Adversarial Net (TAC-GAN) that further benefits from a new player that interacts with other players (the generator and the discriminator) in GAN. Theoretically, we demonstrate that TAC-GAN can effectively minimize the divergence between the generated and real-data distributions. Extensive experimental results show that our TAC-GAN can successfully replicate the true data distributions on simulated data, and significantly improves the diversity of class-conditional image generation on real datasets.
80 - Nicolas Le Roux 2016
The standard approach to supervised classification involves the minimization of a log-loss as an upper bound to the classification error. While this is a tight bound early on in the optimization, it overemphasizes the influence of incorrectly classif ied examples far from the decision boundary. Updating the upper bound during the optimization leads to improved classification rates while transforming the learning into a sequence of minimization problems. In addition, in the context where the classifier is part of a larger system, this modification makes it possible to link the performance of the classifier to that of the whole system, allowing the seamless introduction of external constraints.
89 - Martin Moeller 2007
We study closures of GL_2(R)-orbits on the total space of the Hodge bundle over the moduli space of curves under the assumption that they are algebraic manifolds. We show that, in the generic stratum, such manifolds are the whole stratum, the hyper elliptic locus or parameterize curves whose Jacobian has additional endomorphisms. This follows from a cohomological description of the tangent bundle to strata. For non-generic strata similar results can be shown by a case-by-case inspection. We also propose to study a notion of linear manifold that comprises Teichmueller curves, Hilbert modular surfaces and the ball quotients of Deligne and Mostow. Moreover, we give an explanation for the difference between Hilbert modular surfaces and Hilbert modular threefolds with respect to this notion of linearity.
334 - Kulin Shah , Naresh Manwani 2019
Active learning is an important technique to reduce the number of labeled examples in supervised learning. Active learning for binary classification has been well addressed in machine learning. However, active learning of the reject option classifier remains unaddressed. In this paper, we propose novel algorithms for active learning of reject option classifiers. We develop an active learning algorithm using double ramp loss function. We provide mistake bounds for this algorithm. We also propose a new loss function called double sigmoid loss function for reject option and corresponding active learning algorithm. We offer a convergence guarantee for this algorithm. We provide extensive experimental results to show the effectiveness of the proposed algorithms. The proposed algorithms efficiently reduce the number of label examples required.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا