Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning
Comments 37th Conference on Neural Information Processing Systems (NeurIPS 2023)
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling
Comments 32 pages, 11 figures, 37th Conference on Neural Information Processing Systems (NeurIPS 2023)
Multiply Robust Federated Estimation of Targeted Average Treatment Effects
Comments Accepted at NeurIPS 2023
User-Level Differential Privacy With Few Examples Per User
Comments To appear at Neural Information Processing Systems (NeurIPS) 2023
DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions
Comments Accepted by NeurIPS 2023
Revisiting Scalarization in Multi-Task Learning: A Theoretical Perspective
Comments Accepted at NeurIPS 2023
SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models
Comments NeurIPS 2023 Spotlight. Project page: https://slotdiffusion.github.io/
Red Teaming Deep Neural Networks with Feature Synthesis Tools
Comments In Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS 2023)
A-NeSI: A Scalable Approximate Method for Probabilistic Neurosymbolic Inference
Comments Accepted to NeurIPS 2023. 13 pages, 11 appendix pages, 7 figures
Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning
Comments NeurIPS 2022 (Spotlight)
Towards Self-Adaptive Pseudo-Label Filtering for Semi-Supervised Learning
Comments This paper was first submitted to NeurIPS 2021
Language models are susceptible to incorrect patient self-diagnosis in medical applications
Comments 4 pages, Deep Generative Models for Health NeurIPS 2023
Equivariant Representation Learning in the Presence of Stabilizers
Comments NeurIPS Workshop on Symmetry and Geometry in Neural Representations (v1), European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (v2)
Inference in High-Dimensional Linear Regression via Lattice Basis Reduction and Integer Relation Detection
Comments 56 pages. Parts of the material of this manuscript were presented at NeurIPS 2018, and ISIT 2019. This submission subsumes the content of arXiv:1803.06716
Journal ref IEEE Transactions on Information Theory (Volume: 67, Issue: 12, December 2021)
Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models
Comments NeurIPS 2022 T-PAMI 2023 Website: https://www.cs.cmu.edu/~sige/ Code: https://github.com/lmxyy/sige
On Computationally Efficient Learning of Exponential Family Distributions
Comments An earlier version of this work arXiv:2110.15397 was presented at the Neural Information Processing Systems Conference in December 2021 titled "A Computationally Efficient Method for Learning Exponential Family Distributions"
Expressive dynamics models with nonlinear injective readouts enable reliable recovery of latent features from neural activity
Comments 11 pages, 6 figures, Submitted to NeurIPS 2023
Robust Feature-Level Adversaries are Interpretability Tools
Comments NeurIPS 2022, code available at https://github.com/thestephencasper/feature_level_adv
Learning to Find Proofs and Theorems by Learning to Refine Search Strategies: The Case of Loop Invariant Synthesis
Journal ref Advances in Neural Information Processing Systems, volume 35 (2022) 4843--4856
Generalised Mutual Information: a Framework for Discriminative Clustering
Comments Submitted for review at the IEEE Transactions on Pattern Analysis and Machine Intelligence. This article is an extension of an original NeurIPS 2022 article [arXiv:2210.06300]
Verification against in-situ observations for Data-Driven Weather Prediction
Comments 10 pages, 6 figures, under review at NeurIPS main conference
Into the Single Cell Multiverse: an End-to-End Dataset for Procedural Knowledge Extraction in Biomedical Texts
Comments Submitted to NeurIPS 2023 Datasets and Benchmarks Track
An analysis of Ermakov-Zolotukhin quadrature using kernels
Journal ref Advances in Neural Information Processing Systems 34 (2021): 27278-27289
Towards solving model bias in cosmic shear forward modeling
Comments 6 pages, accepted to the Machine Learning and the Physical Sciences Workshop at NeurIPS 2022; added acknowledgments
BenchTemp: A General Benchmark for Evaluating Temporal Graph Neural Networks
Comments 28 pages, 23 figures, 27 tables. Submitted to the Conference on Neural Information Processing Systems 2023 Track on Datasets and Benchmarks
Visual correspondence-based explanations improve AI robustness and human-AI team accuracy
Comments NeurIPS 2022 conference paper
Domain Generalization without Excess Empirical Risk
Comments Published at NeurIPS 2022
RecXplainer: Amortized Attribute-based Personalized Explanations for Recommender Systems
Comments Awarded the Best Student Paper at TEA Workshop at NeurIPS 2022
On the Existence of the Adversarial Bayes Classifier (Extended Version)
Comments 27 pages, 3 figures. Version 2: Corrects 2 errors in the paper "On the Existence of the Adversarial Bayes Classifier" published in NeurIPS. Version 3: Update to acknowledgements
Target-independent XLA optimization using Reinforcement Learning
Comments Workshop on ML for Systems @ NeurIPS 2022
