Zobrazeno 1 - 10
of 96
pro vyhledávání: '"Prater-Bennette A"'
Distributionally robust optimization (DRO) is a powerful framework for training robust models against data distribution shifts. This paper focuses on constrained DRO, which has an explicit characterization of the robustness level. Existing studies on
Externí odkaz:
http://arxiv.org/abs/2404.01200
This paper introduces a nonconvex approach for sparse signal recovery, proposing a novel model termed the $\tau_2$-model, which utilizes the squared $\ell_1/\ell_2$ norms for this purpose. Our model offers an advancement over the $\ell_0$ norm, which
Externí odkaz:
http://arxiv.org/abs/2404.00764
This paper investigates the computation of proximity operators for scale and signed permutation invariant functions. A scale-invariant function remains unchanged under uniform scaling, while a signed permutation invariant function retains its structu
Externí odkaz:
http://arxiv.org/abs/2404.00713
Multi-task and multi-domain learning methods seek to learn multiple tasks/domains, jointly or one after another, using a single unified network. The key challenge and opportunity is to exploit shared information across tasks and domains to improve th
Externí odkaz:
http://arxiv.org/abs/2310.06124
Multimodal learning seeks to utilize data from multiple sources to improve the overall performance of downstream tasks. It is desirable for redundancies in the data to make multimodal systems robust to missing or corrupted observations in some correl
Externí odkaz:
http://arxiv.org/abs/2310.03986
Leveraging information across diverse modalities is known to enhance performance on multimodal segmentation tasks. However, effectively fusing information from different modalities remains challenging due to the unique characteristics of each modalit
Externí odkaz:
http://arxiv.org/abs/2309.04001
Robust Markov decision processes (MDPs) address the challenge of model uncertainty by optimizing the worst-case performance over an uncertainty set of MDPs. In this paper, we focus on the robust average-reward MDPs under the model-free setting. We fi
Externí odkaz:
http://arxiv.org/abs/2305.10504
In robust Markov decision processes (MDPs), the uncertainty in the transition kernel is addressed by finding a policy that optimizes the worst-case performance over an uncertainty set of MDPs. While much of the literature has focused on discounted MD
Externí odkaz:
http://arxiv.org/abs/2301.00858
Autor:
Hyder, Rakib, Shao, Ken, Hou, Boyu, Markopoulos, Panos, Prater-Bennette, Ashley, Asif, M. Salman
Publikováno v:
ECCV 2022
Incremental Task learning (ITL) is a category of continual learning that seeks to train a single network for multiple tasks (one after another), where training data for each task is only available during the training of that task. Neural networks ten
Externí odkaz:
http://arxiv.org/abs/2207.09074
Publikováno v:
IEEE Open Journal of Signal Processing, Vol 5, Pp 599-610 (2024)
Leveraging information across diverse modalities is known to enhance performance on multimodal segmentation tasks. However, effectively fusing information from different modalities remains challenging due to the unique characteristics of each modalit
Externí odkaz:
https://doaj.org/article/1f4d4adf362248788393e48daa7bcbc4
