Timur Garipov
Novosibirsk State University(RU)
Publications by Year
Research Areas
Adversarial Robustness in Machine Learning, Domain Adaptation and Few-Shot Learning, Natural Language Processing Techniques, Advanced Neural Network Applications, Gaussian Processes and Bayesian Inference
Most-Cited Works
- Averaging Weights Leads to Wider Optima and Better Generalization(2018)
- → Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs(2018)212 cited
- → A Simple Baseline for Bayesian Uncertainty in Deep Learning(2019)181 cited
- → Ultimate tensorization: compressing convolutional and FC layers alike(2016)102 cited
- Subspace Inference for Bayesian Deep Learning(2019)
- Towards understanding the true loss surface of deep neural networks using random matrix theory and iterative spectral methods(2019)
- → Bayesian Incremental Learning for Deep Neural Networks(2018)10 cited