Scalable Learning and MAP Inference for Nonsymmetric Determinantal Point Processes
Comments ICLR 2021
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
Generalization bounds via distillation
Comments To appear, ICLR 2021
Understanding Overparameterization in Generative Adversarial Networks
Comments Accepted in ICLR 2021
Sparse Coding Frontend for Robust Neural Networks
Comments International Conference on Learning Representations (ICLR) 2021 Workshop on Security and Safety in Machine Learning Systems
How Sensitive are Meta-Learners to Dataset Imbalance?
Comments Published as a workshop paper at the Learning to Learn workshop at ICLR 2021. arXiv admin note: text overlap with arXiv:2101.02523
ALT-MAS: A Data-Efficient Framework for Active Testing of Machine Learning Algorithms
Comments Accepted to the RobustML workshop at ICLR 2021
Detection of COVID-19 Disease using Deep Neural Networks with Ultrasound Imaging
Comments Practical ML for Developing Countries Workshop at ICLR 2021
GraphEBM: Molecular Graph Generation with Energy-Based Models
Comments Accepted by Energy-Based Models Workshop ICLR 2021
Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning
Comments 49 pages, 7 figures; ICLR 2021 camera ready
Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth
Comments ICLR 2021
SI-Score: An image dataset for fine-grained analysis of robustness to object location, rotation and size
Comments 4 pages (10 pages including references and appendix), 10 figures. Accepted at the ICLR 2021 RobustML Workshop. arXiv admin note: text overlap with arXiv:2007.08558
Self-Supervised Policy Adaptation during Deployment
Comments Website: https://nicklashansen.github.io/PAD/ Code: https://github.com/nicklashansen/policy-adaptation-during-deployment ICLR 2021
A Design Space Study for LISTA and Beyond
Comments Published as a conference paper at ICLR 2021
Improving Solar Cell Metallization Designs using Convolutional Neural Networks
Comments Published as a workshop paper at ICLR 2021 SimDL Workshop
Evaluations and Methods for Explanation through Robustness Analysis
Comments To appear in ICLR 2021
Probing BERT in Hyperbolic Spaces
Comments ICLR 2021 Camera ready
Post-Hoc Domain Adaptation via Guided Data Homogenization
Comments Published as a conference paper at ICLR 2021; 4 pages, plus appendix, 5 figures
PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics
Comments Accepted to ICLR 2021 as a spotlight presentation. Project page: http://plasticinelab.csail.mit.edu/
The Emergence of Abstract and Episodic Neurons in Episodic Meta-RL
Comments This work was accepted at the Learning to Learn Workshop (ICLR 2021)
On the Critical Role of Conventions in Adaptive Human-AI Collaboration
Comments 9th International Conference on Learning Representations (ICLR 2021)
In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness
Comments ICLR 2021
Bowtie Networks: Generative Modeling for Joint Few-Shot Recognition and Novel-View Synthesis
Comments Accepted as a Poster paper at ICLR 2021
Learning Invariant Representations for Reinforcement Learning without Reconstruction
Comments Accepted as an oral at ICLR 2021
AutoHAS: Efficient Hyperparameter and Architecture Search
Comments Accepted to 2nd Workshop on Neural Architecture Search at ICLR 2021
gradSim: Differentiable simulation for system identification and visuomotor control
Comments ICLR 2021. Project page (and a dynamic web version of the article): https://gradsim.github.io
Shapley Explanation Networks
Comments 26 pages, 11 figures, accepted to ICLR 2021
Contrastive Syn-to-Real Generalization
Comments Accepted in ICLR 2021
Beyond Categorical Label Representations for Image Classification
Comments International Conference on Learning Representations (ICLR 2021). Project page is at \url{https://www.creativemachineslab.com/label-representation.html}
Neural Pruning via Growing Regularization
Comments Accepted by ICLR 2021
Journal ref International Conference on Learning Representations (ICLR) 2021
Reinforcement Learning with Chromatic Networks for Compact Architecture Search
Comments Published at ICLR 2020 Neural Architecture Search Workshop. This paper is deprecated; please see arXiv:2101.07415 for the newer version
