Not All Lotteries Are Made Equal
Comments Accepted at ICML 2022 HAET Workshop
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Fault-Tolerant Collaborative Inference through the Edge-PRUNE Framework
Comments Accepted to ICML 2022 Workshop on Dynamic Neural Networks (DyNN)
On Private Online Convex Optimization: Optimal Algorithms in $\ell_p$-Geometry and High Dimensional Contextual Bandits
Comments This is the extended version of the paper appeared in the 39th International Conference on Machine Learning (ICML 2022): Optimal Private Streaming SCO in $\ell_p$-geometry with Applications in High Dimensional Online Decision Making
Closed-Form Diffeomorphic Transformations for Time Series Alignment
Comments 37 pages, 24 figures, 4 tables. Accepted at International Conference on Machine Learning ICML 2022
Active Nearest Neighbor Regression Through Delaunay Refinement
Comments Accepted at the International Conference on Machine Learning (ICML) 2022
Generalized Leverage Scores: Geometric Interpretation and Applications
Comments ICML 2022
Balancing Discriminability and Transferability for Source-Free Domain Adaptation
Comments ICML 2022. Project page: https://sites.google.com/view/mixup-sfda
Continual Learning with Guarantees via Weight Interval Constraints
Comments Short presentation at ICML 2022
Personalized Federated Learning via Variational Bayesian Inference
Comments accepted for publication in 39th International Conference on Machine Learning (ICML), 2022
Optimization-Derived Learning with Essential Convergence Analysis of Training and Hyper-training
Comments Accepted by ICML 2022
Conformal prediction set for time-series
Comments Strongly accepted by the Workshop on Distribution-Free Uncertainty Quantification at ICML 2022
Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness
Comments Accepted by ICML 2022
HyperImpute: Generalized Iterative Imputation with Automatic Model Selection
Journal ref In Proc. 39th International Conference on Machine Learning (ICML 2022)
$O(N^2)$ Universal Antisymmetry in Fermionic Neural Networks
Comments ICML 2022 AI for Science Workshop
Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration
Comments ICML 2022; The first sequence-to-sequence model for video restoration
Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencoder
Comments ICML 2022, code is available at https://github.com/WonderSeven/LSSAE
Equivariant Diffusion for Molecule Generation in 3D
Comments Accepted at International Conference on Machine Learning (ICML) 2022
Robustness and Accuracy Could Be Reconcilable by (Proper) Definition
Comments ICML 2022
Dataset Condensation with Contrastive Signals
Comments Accepted at ICML 2022
FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
Comments Accepted by The 39th International Conference on Machine Learning (ICML 2022)
Adversarial Attacks on Gaussian Process Bandits
Comments Accepted to ICML 2022
Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Them
Comments ICML 2022 (Long Talk)
A Tree-based Model Averaging Approach for Personalized Treatment Effect Estimation from Heterogeneous Data Sources
Comments Accepted at ICML 2022. Previously titled "A Tree-based Federated Learning Approach for Personalized Treatment Effect Estimation from Heterogeneous Data Sources"
Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling
Comments ICML 2022
Epistemic Deep Learning
Comments Accepted at ICML 2022 Workshop on Distribution-Free Uncertainty Quantification
Calibrating Agent-based Models to Microdata with Graph Neural Networks
Comments Accepted for a Spotlight presentation at the ICML 2022 Artificial Intelligence for Agent-based Modelling (AI4ABM) Workshop
A Meta-Analysis of Distributionally-Robust Models
Comments To be presented at ICML Workshop on Principles of Distribution Shift 2022. Copyright 2022 by the author(s)
Linear Complexity Randomized Self-attention Mechanism
Comments ICML 2022 camera ready with 37 pages
Transfer and Marginalize: Explaining Away Label Noise with Privileged Information
Comments Accepted at ICML 2022, Baltimore
CITRIS: Causal Identifiability from Temporal Intervened Sequences
Comments Accepted at the International Conference on Machine Learning (ICML), 2022
