Asia
Adapting to Continuous Covariate Shift via Online Density Ratio Estimation Y u-Jie Zhang
Existing works of coping with covariate shift mainly focused on the "
k-Means Clustering of Lines for Big Data
Neural Information Processing Systems http://nips.cc/
RobustnessAnalysisofVideo-LanguageModels AgainstVisualandLanguagePerturbations
Joint visual and language modeling on large-scale datasets has recently shown good progress in multi-modal tasks when compared to single modal learning.
Semi-supervised Knowledge Transfer Across Multi-omic Single-cell Data
Code is available at https://github.com/zfkarl/DANCE.
Variance Reduced Policy Evaluation with Smooth Function Approximation
Hoi-To Wai, Mingyi Hong, Zhuoran Yang, Zhaoran Wang, Kexin Tang
Neural Information Processing Systems http://nips.cc/
Is Deeper Better only when Shallow is Good?
Eran Malach, Shai Shalev-Shwartz
While current works account for the importance ofdepth for the expressivepower ofneural-networks, itremains an open question whether these benefits are exploited during a gradient-based optimization process.
TemporalEffectiveBatchNormalizationinSpiking NeuralNetworks
Furthermore, the temporal dynamics of spiking neuron is tightly in connection with the neuronal parameters.
Simple and Fast Distillation of Diffusion Models Zhenyu Zhou 1,2 Defang Chen 3 Can Wang 1,2 Chun Chen
To achieve both efficient and high-quality synthesis, various distillation-based accelerated sampling methods have been developed recently.
