Bad-Policy Density: A Measure of Reinforcement Learning Hardness
Comments Presented at the 2021 ICML Workshop on Reinforcement Learning Theory
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Detecting and Quantifying Malicious Activity with Simulation-based Inference
Comments Short version, appeared at ICML workshop on Socially Responsible Machine Learning 2021
Exponentially Many Local Minima in Quantum Neural Networks
Comments 27 pages, 10 figures
Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12144-12155, 2021
Sample-Optimal PAC Learning of Halfspaces with Malicious Noise
Comments Accepted to ICML 2021. V2 and V3 polished writing
An Empirical Investigation of Learning from Biased Toxicity Labels
Comments 8 pages, 6 figures. Accepted to the Socially Responsible Machine Learning Workshop, ICML 2021
A Aelf-supervised Tibetan-chinese Vocabulary Alignment Method Based On Adversarial Learning
Comments 8pages,2nd International Conference on Machine Learning Techniques and NLP (MLNLP 2021)
Journal ref Advances in Machine Learning, Data Mining and Computing 2nd International Conference on Machine Learning Techniques and NLP (MLNLP 2021) Volume 11, Number 14, September 2021
Consistency Regularization Can Improve Robustness to Label Noise
Comments Presented at the ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning. arXiv admin note: text overlap with arXiv:2105.04522
Learning disentangled representations via product manifold projection
Comments 15 pages, 10 figures
Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139, 2021
Really Useful Synthetic Data -- A Framework to Evaluate the Quality of Differentially Private Synthetic Data
Journal ref Workshop on Economics of Privacy and Data Labor, 37th International Conference on Machine Learning, Vienna, Austria, 2020
Sparse Data Generation for Particle-Based Simulation of Hadronic Jets in the LHC
Comments 4 pages, 2 figures, 1 table. Contribution to Proceedings of the LatinX in AI (LXAI) Research workshop at ICML 2021
How Different Text-preprocessing Techniques Using The BERT Model Affect The Gender Profiling of Authors
Journal ref Advances in Machine Learning 3rd International Conference on Machine Learning & Applications (CMLA 2021), September 25~26, 2021, Toronto, Canada Volume Editors : David C. Wyld, Dhinaharan Nagamalai (Eds) ISBN : 978-1-925953-49-7
A PAC-Bayesian Analysis of Distance-Based Classifiers: Why Nearest-Neighbour works!
Comments This article was submitted to ICML 2000 and rejected; the references have not been updated since the submission in 2000
Survey of Visual-Semantic Embedding Methods for Zero-Shot Image Retrieval
Comments Accepted by 20th IEEE International Conference on Machine Learning and Applications (ICMLA2021)
TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models
Comments ICML 2021
Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message
Comments Appeared in ICML'21
Just Train Twice: Improving Group Robustness without Training Group Information
Comments International Conference on Machine Learning (ICML), 2021
Non-Convex Exact Community Recovery in Stochastic Block Model
Comments A preliminary version of this work has appeared in the Proceedings of the 37th International Conference on Machine Learning (ICML 2020). This version is accepted for publication in Mathematical Programming
Formalizing Distribution Inference Risks
Comments ICML 2021 Workshop on Theory and Practice of Differential Privacy. Longer version of work available at arXiv:2109.06024 Update: Labelling error for Census[Race], where graphs were mirror-images because of 1-ratio being used instead of the ratio. Comparison with SOTA also updated; conclusions remain unchanged
SAINT-ACC: Safety-Aware Intelligent Adaptive Cruise Control for Autonomous Vehicles Using Deep Reinforcement Learning
Comments Accepted for publication in ICML, 2021
Journal ref Proceedings of the 38th International Conference on Machine Learning (2021) 2445-2455
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
GRAND: Graph Neural Diffusion
Comments 15 pages, 4 figures. Proceedings of the 38th International Conference on Machine Learning, PMLR 139, 2021. Copyright 2021 by the author(s)
An Empirical Evaluation of the t-SNE Algorithm for Data Visualization in Structural Engineering
Comments This paper has been accepted for publication in IEEE International Conference on Machine Learning and Applications 2021
Self-Supervised Neural Architecture Search for Imbalanced Datasets
Comments Published in ICML 2021 Workshop: Self-Supervised Learning for Reasoning and Perception. Code: https://github.com/TimofeevAlex/ssnas_imbalanced
TFPnP: Tuning-free Plug-and-Play Proximal Algorithm with Applications to Inverse Imaging Problems
Comments The Journal version (47 pages) of arXiv:2002.09611 (ICML'20 Award Paper); Code is released at https://github.com/Vandermode/TFPnP
Unifying task specification in reinforcement learning
Comments Published at the International Conference on Machine Learning, 2017. This version includes minor typo and error fixes
Comparison and Unification of Three Regularization Methods in Batch Reinforcement Learning
Comments ICML Workshop on Reinforcement Learning Theory 2021
Efficient Differentiable Simulation of Articulated Bodies
Comments ICML 2021
Neighborhood Contrastive Learning Applied to Online Patient Monitoring
Comments ICML 2021
Journal ref Proceedings of 38th International Conference on Machine Learning, 139, (2021) 11964--11974
Convergence of a Human-in-the-Loop Policy-Gradient Algorithm With Eligibility Trace Under Reward, Policy, and Advantage Feedback
Comments Accepted into ICML 2021 workshops Human-AI Collaboration in Sequential Decision-Making and Human in the Loop Learning
Adversarial for Good? How the Adversarial ML Community's Values Impede Socially Beneficial Uses of Attacks
Comments Author list is ordered alphabetically as there is equal contribution. 4 pages Accepted by the ICML 2021 workshop on "A Blessing in Disguise:The Prospects and Perils of Adversarial Machine Learning"
