Statistical Learning
L VM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching Duy M. H. Nguyen
Obtaining large pre-trained models that can be fine-tuned to new tasks with limited annotated samples has remained an open challenge for medical imaging data.
Understanding the Role of Momentum in Stochastic Gradient Methods
Igor Gitman, Hunter Lang, Pengchuan Zhang, Lin Xiao
Different variants ofmomentum, including heavyball momentum, Nesterov's accelerated gradient (NAG), and quasi-hyperbolic momentum (QHM), havedemonstrated success onvarious tasks. Our results are most closely related to the work of Mandt et al.[19]who use stationaryanalysis of SGD with momentum to perform approximateBayesianinference.
Learning SMaLL Predictors
Vikas Garg, Ofer Dekel, Lin Xiao
Neural Information Processing Systems http://nips.cc/
Twin Auxilary Classifiers GAN
Mingming Gong, Yanwu Xu, Chunyuan Li, Kun Zhang, Kayhan Batmanghelich
Neural Information Processing Systems http://nips.cc/
Communication-Efficient Distributed Learning via Lazily Aggregated Quantized Gradients
Jun Sun, Tianyi Chen, Georgios Giannakis, Zaiyue Yang
Neural Information Processing Systems http://nips.cc/
A Spectral View of Adversarially Robust Features
Shivam Garg, Vatsal Sharan, Brian Zhang, Gregory Valiant
Neural Information Processing Systems http://nips.cc/
Analytic solution and stationary phase approximation for the Bayesian lasso and elastic net
The lasso and elastic net linear regression models impose a double-exponential prior distribution on the model parameters to achieve regression shrinkage and variable selection, allowing the inference of robust models from large data sets.
Contextual bandits with surrogate losses: Margin bounds and efficient algorithms
Dylan J. Foster, Akshay Krishnamurthy
Neural Information Processing Systems http://nips.cc/