FedGEMS: Federated Learning of Larger Server Models via Selective Knowledge Fusion
Comments Under review as a conference paper at ICLR 2022
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
δ-CLUE: Diverse Sets of Explanations for Uncertainty Estimates
Comments Appeared as a workshop paper at ICLR 2021 (Responsible AI | Secure ML | Robust ML)
Structured Prediction as Translation between Augmented Natural Languages
Journal ref International Conference on Learning Representations (ICLR) 2021
Regularization Matters in Policy Optimization
Comments Published at ICLR 2021; please cite this paper's ICLR 2021 version at https://github.com/xuanlinli17/iclr2021_rlreg#citation or the arXiv version from "Export Bibtex Citation" on the right, instead of the "2019 OpenReview" version in Google Scholar. Thanks!
Removing Undesirable Feature Contributions Using Out-of-Distribution Data
Comments Published as a conference paper at ICLR 2021
Emergent Road Rules In Multi-Agent Driving Environments
Comments International Conference on Learning Representations (2021)
Journal ref International Conference on Learning Representations, 2021
Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphs
Comments Published at ICLR 2021
Adversarial Training Methods for Semi-Supervised Text Classification
Comments Published as a conference paper at ICLR 2017
Federated Learning Based on Dynamic Regularization
Comments Slightly extended version of ICLR 2021 Paper
VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models
Comments ICLR 2021 (spotlight)
Sequence-to-Sequence Modeling for Action Identification at High Temporal Resolution
Comments Under review as a conference paper at ICLR 2022
DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning
Comments 10 pages, 5 figures, submitted to ICLR 2022
Discovering Non-monotonic Autoregressive Orderings with Variational Inference
Comments updated from ICLR 2021, first two authors contributed equally
Learning Neural Event Functions for Ordinary Differential Equations
Journal ref ICLR 2021
Adaptive Universal Generalized PageRank Graph Neural Network
Comments ICLR 2021
Learning Robust Controllers Via Probabilistic Model-Based Policy Search
Comments Accepted at RobustML Workshop - ICLR 2021
On the Variance of the Adaptive Learning Rate and Beyond
Comments ICLR 2020. Fix several typos in the previous version
Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning
Comments ICLR 2021. First two authors contributed equally. Website: https://agarwl.github.io/iup/
Auction learning as a two-player game
Journal ref The 9th International Conference on Learning Representations, ICLR 2021
Center Loss Regularization for Continual Learning
Comments 16 pages, 9 figures, Submitted to the ICLR 2022 conference
On the benefits of defining vicinal distributions in latent space
Comments Accepted at Elsevier Pattern Recognition Letters (2021), Best Paper Award at CVPR 2021 Workshop on Adversarial Machine Learning in Real-World Computer Vision (AML-CV), Also accepted at ICLR 2021 Workshops on Robust-Reliable Machine Learning (Oral) and Generalization beyond the training distribution (Abstract)
Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning
Comments Published as a conference paper at ICLR 2021. Source code available at https://github.com/dayu11/Gradient-Embedding-Perturbation
FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning
Comments Accepted to ICLR 2021; the camera-ready version with code URL
Evaluating model-based planning and planner amortization for continuous control
Comments 9 pages main text, 30 pages with references and appendix including several ablations and additional experiments. Submitted to ICLR 2022
VA-RED$^2$: Video Adaptive Redundancy Reduction
Comments Accepted in ICLR 2021
Active Refinement for Multi-Label Learning: A Pseudo-Label Approach
Comments A preliminary version appeared in the Workshop on Learning from Limited Labeled Data @ ICLR 2019
Ask Your Humans: Using Human Instructions to Improve Generalization in Reinforcement Learning
Comments Accepted at ICLR 2021
Benchmarking Bonus-Based Exploration Methods on the Arcade Learning Environment
Comments Accepted at the second Exploration in Reinforcement Learning Workshop at the 36th International Conference on Machine Learning, Long Beach, California. The full version arxiv.org/abs/2109.11052 was published as a conference paper at ICLR 2020
On Bonus-Based Exploration Methods in the Arcade Learning Environment
Comments Full version of arXiv:1908.02388
Journal ref Published as a conference paper at ICLR 2020
A Gradient Flow Framework For Analyzing Network Pruning
Comments Accepted at ICLR, 2021
