A Large-Scale Study of Probabilistic Calibration in Neural Network Regression
Comments Accepted at the 40th International Conference on Machine Learning (ICML 2023)
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Meta-SAGE: Scale Meta-Learning Scheduled Adaptation with Guided Exploration for Mitigating Scale Shift on Combinatorial Optimization
Comments 18 pages, 9 figures, International Conference on Machine Learning (ICML) 2023
Auto-Differentiation of Relational Computations for Very Large Scale Machine Learning
Comments ICML 2023
Extrapolative Controlled Sequence Generation via Iterative Refinement
Comments ICML 2023 - Camera Ready Version
Streaming Active Learning with Deep Neural Networks
Comments ICML 2023
A Modern Look at the Relationship between Sharpness and Generalization
Comments The camera-ready version (accepted at ICML 2023)
Rigid Body Flows for Sampling Molecular Crystal Structures
Comments International Conference on Machine Learning, 2023
Answering Complex Logical Queries on Knowledge Graphs via Query Computation Tree Optimization
Comments To appear in ICML 2023
SinDDM: A Single Image Denoising Diffusion Model
Comments Updated for ICML 2023 and added the Appendix. Note that the images are lightly compressed. Visit our project page for uncompressed results: https://matankleiner.github.io/sinddm/
Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning
Comments Appears in: Fortieth International Conference on Machine Learning (ICML 2023). 36 pages
Learning to Suggest Breaks: Sustainable Optimization of Long-Term User Engagement
Comments Accepted for publication in ICML 2023
Global Contrastive Batch Sampling via Optimization on Sample Permutations
Comments ICML 2023; 21 pages, 7 figures
Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerability
Comments ICML 2023
SGD with Large Step Sizes Learns Sparse Features
Comments The camera-ready version (ICML 2023): extended experiments on deep networks (DenseNets on CIFAR-10, CIFAR-100, and Tiny ImageNet), empirically validated the SDE modelling, improved the clarity of the paper
A Fast, Well-Founded Approximation to the Empirical Neural Tangent Kernel
Journal ref Published at ICML 2023
Neural Diffusion Processes
Comments 23 pages, Proceedings of the 40th International Conference on Machine Learning, PMLR 202
DevFormer: A Symmetric Transformer for Context-Aware Device Placement
Comments International Conference on Machine Learning (ICML) 2023. Extended version of NeurIPS 2022 Offline RL Workshop "Collaborative symmetricity exploitation for offline learning of hardware design solver"
Invariance in Policy Optimisation and Partial Identifiability in Reward Learning
Comments ICML 2023. 9 pages main paper, 26 pages total, 3 figures
Vector-Valued Control Variates
Comments Accepted for publication at ICML 2023
Ewald-based Long-Range Message Passing for Molecular Graphs
Comments Published at the 40th International Conference on Machine Learning (ICML 2023)
Stochastic Gradient Descent-Induced Drift of Representation in a Two-Layer Neural Network
Comments International Conference on Machine Learning (ICML) 2023
Overcoming Simplicity Bias in Deep Networks using a Feature Sieve
Comments Accepted at ICML 2023
Concept-based Explanations for Out-Of-Distribution Detectors
Comments Paper published at International Conference on Machine Learning (ICML'23)
A Novel Approach To User Agent String Parsing For Vulnerability Analysis Using Mutli-Headed Attention
Comments Accepted to the International Conference on Machine Learning and Cybernetics (ICMLC) 2023
Exploring Model Dynamics for Accumulative Poisoning Discovery
Comments accepted by ICML 2023
Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability
Comments accepted by ICML 2023
Buying Information for Stochastic Optimization
Comments To appear in ICML 2023
Memory-Based Dual Gaussian Processes for Sequential Learning
Comments International Conference on Machine Learning (ICML) 2023
On Pitfalls of Test-Time Adaptation
Comments Accepted at ICML 2023
GRAFENNE: Learning on Graphs with Heterogeneous and Dynamic Feature Sets
Comments 17 pages, 4 figures and 9 tables. Accepted in ICML 2023, DOI will be updated once it is available
