Sample-Conditioned Hypothesis Stability Sharpens Information-Theoretic Generalization Bounds
Comments Accepted at NeurIPS 2023
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
Robust Learning for Smoothed Online Convex Optimization with Feedback Delay
Comments Accepted by NeurIPS 2023
$p$-Poisson surface reconstruction in curl-free flow from point clouds
Comments 21 pages, accepted for Advances in Neural Information Processing Systems, 2023
Estimating optimal PAC-Bayes bounds with Hamiltonian Monte Carlo
Comments Mathematics of Modern Machine Learning Workshop at NeurIPS 2023
Scaling Riemannian Diffusion Models
Comments NeurIPS 2023
Multiscale Feature Attribution for Outliers
Comments 6 pages, 2 figures, accepted to NeurIPS 2023 Workshop on Machine Learning and the Physical Sciences. Code available at https://github.com/al-jshen/imo
Scaling Up Differentially Private LASSO Regularized Logistic Regression via Faster Frank-Wolfe Iterations
Comments To appear in the 37th Conference on Neural Information Processing Systems (NeurIPS 2023)
ExPT: Synthetic Pretraining for Few-Shot Experimental Design
Comments 2023 Conference on Neural Information Processing Systems (NeurIPS)
Sim2Real for Environmental Neural Processes
Comments 4 pages, 3 figures, To be published in Tackling Climate Change with Machine Learning workshop at NeurIPS
Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms
Comments Published at NeurIPS 2023
Bayesian Simulation-based Inference for Cosmological Initial Conditions
Comments Accepted for the NeurIPS 2023 workshop Machine Learning and the Physical Sciences; 5 pages, 1 figure
Exploring Geometry of Blind Spots in Vision Models
Comments 25 pages, 20 figures, Accepted at NeurIPS 2023 (spotlight)
Posterior Sampling for Competitive RL: Function Approximation and Partial Observation
Comments NeurIPS 2023
Res-Tuning: A Flexible and Efficient Tuning Paradigm via Unbinding Tuner from Backbone
Comments Accepted to NeurIPS 2023
Improved Communication Efficiency in Federated Natural Policy Gradient via ADMM-based Gradient Updates
Comments Accepted at the 37th Conference on Neural Information Processing Systems (NeurIPS 2023)
ShanshuiDaDA: An Interactive, Generative System towards Chinese Shanshui Painting
Comments 4 pages, Machine Learning for Creativity and Design Workshop, the 32nd Conference on Neural Information Processing Systems (NIPS 2018), Montreal, Canada. See: https://nips2018creativity.github.io/doc/shanshui_dada.pdf
MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks
Comments 34 pages, 7 figures. NeurIPS 2023
BERT Lost Patience Won't Be Robust to Adversarial Slowdown
Comments Accepted to NeurIPS 2023 [Poster]
Behavior Alignment via Reward Function Optimization
Comments (Spotlight) Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023)
Predicting a Protein's Stability under a Million Mutations
Comments NeurIPS 2023. Code available at https://github.com/jozhang97/MutateEverything
D-Separation for Causal Self-Explanation
Comments NeurIPS 2023
SwiFT: Swin 4D fMRI Transformer
Comments NeurIPS 2023
Censored Sampling of Diffusion Models Using 3 Minutes of Human Feedback
Comments Published in NeurIPS 2023
Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis
Comments NeurIPS 2023 spotlight
Separable Physics-Informed Neural Networks
Comments To appear in NeurIPS 2023 (28 pages, 13 figures). workshop paper: arXiv:2211.08761
Propagating Knowledge Updates to LMs Through Distillation
Comments NeurIPS 2023 Camera Ready
On the Robustness of Removal-Based Feature Attributions
Comments NeurIPS camera-ready version
TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models
Comments Accepted by NeurIPS'23
How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources
Comments 18 pages, 6 figure, 10 tables. NeurIPS 2023 Datasets and Benchmarks Track Camera Ready
Learning Transformer Programs
Comments NeurIPS 2023 (oral). Our code is available at https://github.com/princeton-nlp/TransformerPrograms
