Training Stronger Baselines for Learning to Optimize
- Tianlong Chen
- Weiyi Zhang
- et al.
- 2020
- NeurIPS 2020
Conference paper
Publications
81 results at NeurIPS 2020
ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training
- Chia-Yu Chen
- Jiamin Ni
- et al.
- 2020
- NeurIPS 2020
Conference paperTinyTL: Reduce Memory, Not Parameters for Efficient On-Device Learning
- Han Cai
- Chuang Gan
- et al.
- 2020
- NeurIPS 2020
Conference paperUltra-Low Precision 4-bit Training of Deep Neural Networks
- Xiao Sun
- Naigang Wang
- et al.
- 2020
- NeurIPS 2020
Conference paperRevisiting the Sample Complexity of Sparse Spectrum Approximation of Gaussian Processes
- Minh Hoang
- Trong Nghia Hoang
- et al.
- 2020
- NeurIPS 2020
Conference paperFinding second-order stationary points efficiently in smooth nonconvex linearly constrained optimization problems
- Songtao Lu
- Meisam Razaviyayn
- et al.
- 2020
- NeurIPS 2020
Conference paperQuantifying the Empirical Wasserstein Distance to a Set of Measures: Beating the Curse of Dimensionality
- Nian Si
- Jose Blanchet
- et al.
- 2020
- NeurIPS 2020
Conference paperAuxiliary Task Reweighting for Minimum-data Learning
- Baifeng Shi
- Judy Hoffman
- et al.
- 2020
- NeurIPS 2020
Conference paperModel Agnostic Learning of Multilevel Explanations
- Karthikeyan Natesan Ramamurthy
- Bhanu Vinzamuri
- et al.
- 2020
- NeurIPS 2020
Conference paperContinuous Regularized Wasserstein Barycenters
- Lingxiao Li
- Aude Genevay
- et al.
- 2020
- NeurIPS 2020
Conference paper