Improved Learning Rates of a Functional Lasso-type SVM with Sparse Multi-Kernel Representation
Dec 6, 2021
Speakers
Shaogao Lv
Speaker · 0 followers
Junhui Wang
Speaker · 0 followers
Jiankun Liu
Speaker · 0 followers
About
In this paper, we provide theoretical results of estimation bounds and excess risk upper bounds for support vector machine (SVM) with sparse multi-kernel representation. These convergence rates for multi-kernel SVM are established by analyzing a Lasso-type regularized learning scheme within composite multi-kernel spaces. It is shown that the oracle rates of convergence of classifiers depend on the complexity of multi-kernels, the sparsity and a Bernstein condition and the sample size, which significantly improves on previous results even for the additive or linear cases. In summary, this paper not only provides unified theoretical results for multi-kernel SVMs, but also enriches the literature on high-dimensional nonparametric classification.In this paper, we provide theoretical results of estimation bounds and excess risk upper bounds for support vector machine (SVM) with sparse multi-kernel representation. These convergence rates for multi-kernel SVM are established by analyzing a Lasso-type regularized learning scheme within composite multi-kernel spaces. It is shown that the oracle rates of convergence of classifiers depend on the complexity of multi-kernels, the sparsity and a Bernstein condition and the sample size, which sign…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Representation Learning for Imitation with Contrastive Fourier Features
Watch later
Ofir Nachum, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Learning Revenue-Maximizing Auctions With Differentiable Matching
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Reinforcement Learning Benchmarks for Traffic Signal Control
Watch later
James Ault, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Uncertainty Quantification and Deep Ensembles
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
HELP: Hardware-adaptive Efficient Latency Prediction for NAS via Meta-Learning
Watch later
Hayeon Lee, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Oral Session 5: Generative Modeling
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%