Multi-Task Classification Hypothesis Space with Improved Generalization Bounds
This paper presents a RKHS, in general, of vector-valued functions intended to be used as hypothesis space for multi-task classification. It extends similar hypothesis spaces that have previously considered in the literature. Assuming this space, an improved Empirical Rademacher Complexity-based generalization bound is derived. The analysis is itself extended to an MKL setting. The connection between the proposed hypothesis space and a Group-Lasso type regularizer is discussed. Finally, experimental results, with some SVM-based Multi-Task Learning problems, underline the quality of the derived bounds and validate the paper's analysis.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationGeneral ClassificationGeneralization BoundsMulti-Task LearningSimilar Papers 제목 키워드 기반
Variational Capsule Encoder
We propose a novel capsule network based variational encoder architecture, called Bayesian capsules (B-Caps), to modulate the mean and standard deviation of the sampling distribution in the latent space. We hypothesized …
Image ReconstructionRepresentation LearningPlaying the lottery with rewards and multiple languages: lottery tickets in RL and NLP
The lottery ticket hypothesis proposes that over-parameterization of deep neural networks (DNNs) aids training by increasing the probability of a "lucky" sub-network initialization being present rather than by helping th…
image-classificationImage ClassificationReinforcement LearningReinforcement Learning (RL)Improved Speech Representations with Multi-Target Autoregressive Predictive Coding
Training objectives based on predictive coding have recently been shown to be very effective at learning meaningful representations from unlabeled speech. One example is Autoregressive Predictive Coding (Chung et al., 20…
speech-recognitionSpeech RecognitionTranslationSource-free Domain Adaptation Requires Penalized Diversity
While neural networks are capable of achieving human-like performance in many tasks such as image classification, the impressive performance of each model is limited to its own dataset. Source-free domain adaptation (SFD…
DiversityDomain Adaptationimage-classificationImage Classification+2Multiplicative Oracle Inequalities for Transductive Learning via Level-Set Aggregation
We revisit transductive learning where predictions are made with the set of all covariates known in advance. In the leave-one-out (LOO) setting, the prediction is made with labels of the remaining sample points and evalu…
Density Estimation