Spectral Gap Regularization of Neural Networks
Comments This is a journal extension of the ICML conference paper by Tam and Dunson (2020), arXiv:2003.00992
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Sparse*BERT: Sparse Models Generalize To New tasks and Domains
Comments Presented at Sparsity in Neural Networks Workshop at ICML 2022, 6 pages, 2 figures, 4 tables
Continual Repeated Annealed Flow Transport Monte Carlo
Comments 21 pages, 6 figures Published at International Conference on Machine Learning (ICML) 2022
Reconstructing the Universe with Variational self-Boosted Sampling
Comments A shorter version of this paper is accepted for spotlight presentation in Machine Learning for Astrophysics Workshop at ICML, 2022
Unified Emulation-Simulation Training Environment for Autonomous Cyber Agents
Comments To be published in the Proceedings of the 5th International Conference on Machine Learning for Networking (MLN'2022)
Near-Optimal Learning of Extensive-Form Games with Imperfect Information
Comments Updated V3 to be consistent with ICML 2022 camera-ready version, with an additional analysis of CFR in full-feedback setting in Appendix F
On the Relationships between Graph Neural Networks for the Simulation of Physical Systems and Classical Numerical Methods
Comments 2nd AI4Science Workshop at the 39th International Conference on Machine Learning (ICML), 2022
Quadratically Regularized Subgradient Methods for Weakly Convex Optimization with Weakly Convex Constraints
Comments This article has been published in International Conference on Machine Learning (ICML), 2020. We didn't post the final version to arxiv soon after publication, which leads to the paper being cited under the old title and causes other confusion. We therefore update it in arxiv to avoid the issues of multiple versions
Feature Reduction Method Comparison Towards Explainability and Efficiency in Cybersecurity Intrusion Detection Systems
Comments Published in 2022 21st IEEE International Conference on Machine Learning and Applications. 8 pages. 5 figures
Journal ref IEEE.ICMLA 21 (2022) 1326-1333
Disentangling Syntax and Semantics in the Brain with Deep Networks
Comments Accepted to ICML 2021
Journal ref International Conference on Machine Learning (ICML), 2021
Falsification-Based Robust Adversarial Reinforcement Learning
Comments 8 pages, 4 figures
Journal ref IEEE International Conference on Machine Learning and Applications (ICMLA), 2020, pp. 205-212
Concept Saliency Maps to Visualize Relevant Features in Deep Generative Models
Comments 18th IEEE International Conference on Machine Learning and Applications (ICMLA)
Improved Tree Search for Automatic Program Synthesis
Comments Proceedings of the 2nd Exploration in Reinforcement Learning Workshop at the 36th International Conference on Machine Learning, 2019
Knowledge Distillation for Efficient Sequences of Training Runs
Comments This paper was accepted by ICML 2022 First Workshop of Pre-training: Perspectives, Pitfalls, and Paths Forward
NOMU: Neural Optimization-based Model Uncertainty
Comments 9 pages + appendix
Journal ref Proceedings of the 39th International Conference on Machine Learning, PMLR 162:8708-8758, 2022
Sleep Quality Prediction from Wearables using Convolution Neural Networks and Ensemble Learning
Comments To appear in proceedings of International Conference on Machine Learning Technologies (ICMLT) 2023
Rethinking Persistent Homology for Visual Recognition
Comments ICML 2022 Workshop on Topology, Algebra, and Geometry in Machine Learning
Robust Simulation-Based Inference in Cosmology with Bayesian Neural Networks
Comments 5 pages, 3 figures. Preliminary version accepted at the ML4Astro Machine Learning for Astrophysics Workshop at the Thirty-ninth International Conference on Machine Learning (ICML 2022). Final version published at Machine Learning: Science and Technology
Journal ref Mach. Learn.: Sci. Technol. 4 01LT01 (2023)
Dissecting Supervised Contrastive Learning
Comments v4 updates: - updated appendix section S1.3 - this includes fixing an oversight in the proofs (Lemma 1 missed an equality condition, which now appears in Lemma 2) - improved figure quality
Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3821-3830, 2021
Unsupervised Representations of Pollen in Bright-Field Microscopy
Comments Accepted at the Workshop on Computational Biology at the International Conference on Machine Learning (ICML) in Long Beach, CA, USA on June 14, 2019
The Power of First-Order Smooth Optimization for Black-Box Non-Smooth Problems
Comments Appears in: Proceedings of the 39th International Conference on Machine Learning (ICML 2022). Reference: https://proceedings.mlr.press/v162/gasnikov22a.html
Active Learning with Combinatorial Coverage
Comments Accepted 2022 IEEE International Conference on Machine Learning and Applications (IEEE ICMLA)
Riemannian CUR Decompositions for Robust Principal Component Analysis
Journal ref ICML workshop on Topological, Algebraic and Geometric Learning (2022): 152-160
UNIREX: A Unified Learning Framework for Language Model Rationale Extraction
Comments ICML 2022
Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and More
Comments Proceedings of the 37th International Conference on Machine Learning (ICML 2020)
A Song of Ice and Fire: Analyzing Textual Autotelic Agents in ScienceWorld
Comments In review at ICML 2023
Quantitative Understanding of VAE as a Non-linearly Scaled Isometric Embedding
Comments Accepted to the International Conference on Machine Learning (ICML) 2021. 40 pages, 29 figures
PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration
Comments The paper has been accepted by The Thirty-ninth International Conference on Machine Learning (ICML 2022) and the Cooperative AI Workshop at 35th Conference on Neural Information Processing Systems (NeurIPS 2021)
Estimating Treatment Effects in Continuous Time with Hidden Confounders
Comments 7 pages. First presentation was at ICML 2022 workshop Continuous time methods for machine learning
History Compression via Language Models in Reinforcement Learning
Comments ICML 2022
