Oceania
Optimal Transport Model Distributional Robustness Van-Anh Nguyen
SAM aims to find a perturbed model within the vicinity of a current model that maximizes the loss over a training set.
TheLabelComplexityofActiveLearningfrom ObservationalData
In this problem, the learner is given observational data - a set of examples selected according to some policy along with their labels - as well as access to the policy that selects the examples, and the goal is to construct a classifier with high performance on an entire population, notjusttheobservational data distribution.
Mรถbius Transformation for Fast Inner Product Search on Graph
Zhixin Zhou, Shulong Tan, Zhaozhuo Xu, Ping Li
Neural Information Processing Systems http://nips.cc/
Factor Group-Sparse Regularization for Efficient Low-Rank Matrix Recovery
Jicong Fan, Lijun Ding, Yudong Chen, Madeleine Udell
This paper develops a new class of nonconvex regularizers for low-rank matrix recovery.
On the Convergence Rate of Training Recurrent Neural Networks
Zeyuan Allen-Zhu, Yuanzhi Li, Zhao Song
Neural Information Processing Systems http://nips.cc/
MG-Net: Learn to Customize QAOA with Circuit Depth Awareness Y ang Qian
Despite these advancements, QAOA's practical efficacy is challenged by the quantum coherence limits of modern quantum devices, as there is a ceiling on the allowable maximum circuit depth
b250de41980b58d34d6aadc3f4aedd4c-Paper-Conference.pdf
It has been applied in areas such as breaking cryptographic systems [1], searching databases [2], and quantum simulation [3, 4], in which it gives a quantum speedup over the best known classical algorithms. With the fast development of quantum hardware, recent results [5-7] have shown quantum advantages in specific tasks.
Implicit Task-DrivenProbabilityDiscrepancy MeasureforUnsupervisedDomainAdaptation
However,most measures overlook the fact that the distributions are not the endproduct oflearning, butare the input of adownstream predictor.