An Empirical Study of the Effectiveness of Using a Replay Buffer on Mode Discovery in GFlowNets
Comments Accepted to ICML 2023 workshop on Structured Probabilistic Inference & Generative Modeling
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Gradient Surgery for One-shot Unlearning on Generative Model
Comments ICML 2023 Workshop on Generative AI & Law
Evaluating GPT-3.5 and GPT-4 on Grammatical Error Correction for Brazilian Portuguese
Comments Download the full source to access the dataset. Accepted to LatinX in AI (LXAI) Research at ICML 2023
Unsupervised Embedding Quality Evaluation
Comments As appeared at the 2nd Annual Workshop on Topology, Algebra, and Geometry in Machine Learning (TAG-ML) at the 40th International Conference on Machine Learning (ICML), Honolulu, Hawaii, USA. 2023
High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance
Comments ICML 2023. 86 pages. Changes in v2: ICML formatting was applied along with minor edits of the text
Ensuring Visual Commonsense Morality for Text-to-Image Generation
Comments Workshop on Challenges in Deployable Generative AI at ICML 2023
Convergence of Proximal Point and Extragradient-Based Methods Beyond Monotonicity: the Case of Negative Comonotonicity
Comments ICML 2023. 28 pages, 2 figures. Changes in V2: missing reference was added. Changes in V3: ICML formatting was applied, missing references were added, Table 1 was added. Code: https://github.com/eduardgorbunov/Proximal_Point_and_Extragradient_based_methods_negative_comonotonicity
Multi-Objective GFlowNets
Comments 23 pages, 8 figures. ICML 2023. Code at: https://github.com/GFNOrg/multi-objective-gfn
Results on Counterfactual Invariance
Comments 5 pages with 6 pages of supplementary. Accepted at the ICML 2023 workshop on Spurious Correlations, Invariance and Stability
Neurosymbolic AI for Reasoning on Biomedical Knowledge Graphs
Comments Proceedings of the $\mathit{40}^{th}$ International Conference on Machine Learning: Workshop on Knowledge and Logical Reasoning in the Era of Data-driven Learning (https://klr-icml2023.github.io/schedule.html). PMLR 202, 2023. Condensed, workshop-ready version of previous survey, arXiv:2302.07200 , which is under review. 13 pages (9 content, 4 references), 3 figures, 1 table
MargCTGAN: A "Marginally'' Better CTGAN for the Low Sample Regime
Comments ICML 2023 Workshop on Deployable Generative AI
Gradient-free training of neural ODEs for system identification and control using ensemble Kalman inversion
Comments 10 pages, 3 figures, Workshop on New Frontiers in Learning, Control, and Dynamical Systems at the International Conference on Machine Learning (ICML), Honolulu, Hawaii, USA, 2023
Does Double Descent Occur in Self-Supervised Learning?
Comments 7 pages, 2 tables, 3 figures. Accepted for the workshop on High-Dimensional Learning Dynamics at ICML 2023
Transformers are Universal Predictors
Comments Neural Compression Workshop (ICML 2023)
Beyond Intuition, a Framework for Applying GPs to Real-World Data
Comments Accepted at the ICML Workshop on Structured Probabilistic Inference and Generative Modelling (2023)
A First Order Meta Stackelberg Method for Robust Federated Learning
Comments Accepted to ICML 2023 Workshop on The 2nd New Frontiers In Adversarial Machine Learning. Associated technical report arXiv:2306.13273
Gradient-Free Structured Pruning with Unlabeled Data
Comments Presented in ICML 2023
DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule
Comments To appear at ICML 2023
Training Discrete Energy-Based Models with Energy Discrepancy
Comments Presented at ICML 2023 Workshop: Sampling and Optimization in Discrete Space (SODS 2023)
Unconstrained Online Learning with Unbounded Losses
Comments 41 pages; ICML 2023; v2: fixed some details in the exposition introducing saddle-point problems
Last-Layer Fairness Fine-tuning is Simple and Effective for Neural Networks
Comments Published at the ICML 2023 Workshop on Spurious Correlations, Invariance, and Stability
A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models
Comments Accepted at ICML 2023. 23 pages, 10 tables, 3 figures
Exploiting Partial Common Information Microstructure for Multi-Modal Brain Tumor Segmentation
Comments 2023 ICML Workshop on Machine Learning for Multimodal Healthcare Data (ML4MHD)
MaxCorrMGNN: A Multi-Graph Neural Network Framework for Generalized Multimodal Fusion of Medical Data for Outcome Prediction
Comments To appear in ML4MHD workshop at ICML 2023
Leveraging Factored Action Spaces for Off-Policy Evaluation
Comments Main paper: 8 pages, 7 figures. Appendix: 30 pages, 17 figures. Accepted at ICML 2023 Workshop on Counterfactuals in Minds and Machines, Honolulu, Hawaii, USA. Camera ready version
A Hierarchy of Normalizing Flows for Modelling the Galaxy-Halo Relationship
Comments 8 pages, 2 figures, accepted for ICML 2023 Workshop on Machine Learning for Astrophysics
Is Task-Agnostic Explainable AI a Myth?
Comments Accepted to 2023 ICML Workshop on Interpretable ML in Healthcare, Honolulu, Hawaii, USA (oral)
CLIPood: Generalizing CLIP to Out-of-Distributions
Comments Accepted by ICML 2023
DoCoFL: Downlink Compression for Cross-Device Federated Learning
Comments ICML 2023
GRAN is superior to GraphRNN: node orderings, kernel- and graph embeddings-based metrics for graph generators
Comments Preprint for The 9th International Conference on machine Learning, Optimization and Data science - LOD 2023
