Offline Policy Optimization in RL with Variance Regularizaton
Comments Old Draft, Offline RL Workshop, NeurIPS'20;
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
Bridging the Gap Between Vision Transformers and Convolutional Neural Networks on Small Datasets
Comments Fix the bug when calculating FLOPs of the models
Journal ref Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS) 2022
Integral Probability Metrics PAC-Bayes Bounds
Comments Accepted to NeurIPS 2022
On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations
Comments Published in Advances in Neural Information Processing Systems 34 (NeurIPS 2021)
Cross-Dataset Propensity Estimation for Debiasing Recommender Systems
Comments In Workshop on Distribution Shifts, 36th Conference on Neural Information Processing Systems (NeurIPS 2022)
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data
Comments NeurIPS 2022. Code: https://github.com/val-iisc/Saddle-LongTail
Beyond Real-world Benchmark Datasets: An Empirical Study of Node Classification with GNNs
Comments Accepted to NeurIPS 2022 Datasets and Benchmarks Track. 21 pages, 15 figures
Knowledge Distillation from A Stronger Teacher
Comments Accepted to NeurIPS 2022
Outcome-Driven Reinforcement Learning via Variational Inference
Comments Published in Advances in Neural Information Processing Systems 34 (NeurIPS 2021)
On the Level Sets and Invariance of Neural Tuning Landscapes
Comments 24 pages, 13 figures. Published in NeurIPS 2022 Workshop on Symmetry and Geometry in Neural Representations, and PMLR volume 197
Parameter-free Dynamic Graph Embedding for Link Prediction
Comments 19 pages, 9 figures, 13 tables, Thirty-Sixth Conference on Neural Information Processing Systems (NeurIPS 2022), preprint version
SAPA: Similarity-Aware Point Affiliation for Feature Upsampling
Comments Accepted to NeurIPS 2022. Code is available at https://github.com/poppinace/sapa
Nearly Optimal Best-of-Both-Worlds Algorithms for Online Learning with Feedback Graphs
Comments Accepted at NeurIPS 2022
An Adaptive Deep RL Method for Non-Stationary Environments with Piecewise Stable Context
Comments NeurIPS 2022
DeepMed: Semiparametric Causal Mediation Analysis with Debiased Deep Learning
Comments Accepted by NeurIPS 2022
Taming Fat-Tailed ("Heavier-Tailed'' with Potentially Infinite Variance) Noise in Federated Learning
Comments Published as a conference paper at NeurIPS 2022
SAGDA: Achieving $\mathcal{O}(ε^{-2})$ Communication Complexity in Federated Min-Max Learning
Comments Published as a conference paper at NeurIPS 2022
Why neural networks find simple solutions: the many regularizers of geometric complexity
Comments Accepted as a NeurIPS 2022 paper
Uncertainty Disentanglement with Non-stationary Heteroscedastic Gaussian Processes for Active Learning
Comments Accepted at NeurIPS Workshop on Gaussian Processes, Spatiotemporal Modeling, and Decision-making Systems, 2023
Robust Graph Structure Learning via Multiple Statistical Tests
Comments Accepted by the NeurIPS 2022. Homepage: https://thomas-wyh.github.io/
Renormalization in the neural network-quantum field theory correspondence
Comments A shorter version of this paper has been accepted in the NeurIPS 2022 workshop: Machine learning and the physical sciences (https://ml4physicalsciences.github.io/2022/)
Towards Neural Variational Monte Carlo That Scales Linearly with System Size
Comments Appeared on NeurIPS 2022 AI for Science Workshop (a non-archival poster presentation)
Challenges and Opportunities of Large Transnational Datasets: A Case Study on European Administrative Crop Data
Comments for associated GitHub repository, see https://github.com/maja601/EuroCrops
Journal ref Workshop on Broadening Research Collaborations in ML (NeurIPS 2022)
Truncated Matrix Power Iteration for Differentiable DAG Learning
Comments Published in NeurIPS 2022
Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo
Comments Published at NeurIPS 2022
Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Neural Networks
Comments Accepted as Oral Presentation at NeurIPS 2022 New Frontiers in Graph Learning Workshop (NeurIPS GLFrontiers 2022)
Exponentially Improving the Complexity of Simulating the Weisfeiler-Lehman Test with Graph Neural Networks
Comments 22 pages,5 figures, published at NeurIPS 2022. Updated funding statements
Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection
Comments NeurIPS 2022
Expander Graph Propagation
Comments Presented at LoG 2022. Best Paper Award at the NeurIPS 2022 Workshop on New Frontiers in Graph Learning (GLFrontiers). 18 pages, 1 figure
Synthesizing Informative Training Samples with GAN
Comments NeurIPS 2022 Workshop on Synthetic Data for Empowering ML Research, https://openreview.net/forum?id=frAv0jtUMfS
