Learning new tricks from old dogs: Multi-source transfer learning from pre-trained networks
- Joshua Ka Wing Lee
- Prasanna Sattigeri
- et al.
- 2019
- NeurIPS 2019
Publications
This is our catalog of publications authored by IBM researchers, in collaboration with the global research community. It’s an ever-growing body of work that shows why IBM is one of the most important contributors to modern computing.
Date
Featured collections
Popular topics
47 results at NeurIPS 2019
Average-case averages: Private algorithms for smooth sensitivity and mean estimation
- Mark Bun
- Thomas Steinke
- 2019
- NeurIPS 2019
A game theoretic approach to class-wise selective rationalization
- Shiyu Chang
- Yang Zhang
- et al.
- 2019
- NeurIPS 2019
Scalable inference of topic evolution via models for latent geometric structures
- Mikhail Yurochkin
- Zhiwei Fan
- et al.
- 2019
- NeurIPS 2019
Tight dimension independent lower bound on the expected convergence rate for diminishing step sizes in sgd
- Phuong Ha Nguyen
- Lam Nguyen
- et al.
- 2019
- NeurIPS 2019
Hierarchical optimal transport for document representation
- Mikhail Yurochkin
- Farzaneh Mirzazadeh
- et al.
- 2019
- NeurIPS 2019
Depth-first proof-number search with heuristic edge cost and application to chemical synthesis planning
- Akihiro Kishimoto
- Beat Buesser
- et al.
- 2019
- NeurIPS 2019
Generalization in generative adversarial networks: A novel perspective from privacy protection
- Bingzhe Wu
- Shiwan Zhao
- et al.
- 2019
- NeurIPS 2019
More is less: Learning efficient video representations by big-little network and depthwise temporal aggregation
- Quanfu Fan
- Chun Fu Chen
- et al.
- 2019
- NeurIPS 2019
Visual concept-metaconcept learning
- Chi Han
- Jiayuan Mao
- et al.
- 2019
- NeurIPS 2019