A Marriage between Adversarial Team Games and 2-player Games: Enabling Abstractions, No-regret Learning, and Subgame Solving
Comments 20 pages; Accepted for publication at ICML 2022
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
NISPA: Neuro-Inspired Stability-Plasticity Adaptation for Continual Learning in Sparse Networks
Comments International Conference on Machine Learning 2022
Channel Importance Matters in Few-Shot Image Classification
Comments Accepted to ICML 2022; code available at https://github.com/Frankluox/Channel_Importance_FSL
GraphFM: Improving Large-Scale GNN Training via Feature Momentum
Comments ICML 2022
Adversarial Audio Synthesis with Complex-valued Polynomial Networks
Comments Accepted as oral presentation in Workshop on Machine Learning for Audio Synthesis at ICML 2022
Exploring speaker enrolment for few-shot personalisation in emotional vocalisation prediction
Comments Proceedings of the ICML Expressive Vocalizations Workshop and Competition held in conjunction with the $\mathit{39}^{th}$ International Conference on Machine Learning, Copyright 2022 by the author(s)
PAC-Net: A Model Pruning Approach to Inductive Transfer Learning
Comments In Proceedings of the 39th International Conference on Machine Learning, Baltimore, Maryland, USA, PMLR 162, 2022
Convergence and Recovery Guarantees of the K-Subspaces Method for Subspace Clustering
Comments This paper is accepted by ICML 2022
SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators
Comments The 39th International Conference on Machine Learning (ICML 2022), 21 pages, 10 figures
A$^3$T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing
Comments Accepted by ICML 2022, 12 pages, 10 figures
NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fields
Comments ICML 2022, the project page: https://syguan96.github.io/NeuroFluid/
Refined Convergence Rates for Maximum Likelihood Estimation under Finite Mixture Models
Comments To appear in the Proceedings of the 39th International Conference on Machine Learning (ICML), 2022
HousE: Knowledge Graph Embedding with Householder Parameterization
Comments Accepted by ICML 2022
REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer
Comments ICML 2022 (Long Oral)
Improved Convergence Rates for Sparse Approximation Methods in Kernel-Based Learning
Comments International Conference on Machine Learning (ICML) 2022
Calibrated Learning to Defer with One-vs-All Classifiers
Comments Accepted at the International Conference on Machine Learning (ICML), 2022
Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching
Comments ICML 2022. Project website: https://sites.google.com/view/smodice/home
Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification
Comments First three authors contributed equally, order chosen randomly. 21 pages, 9 figures. Published at ICML 2022
Lightweight Projective Derivative Codes for Compressed Asynchronous Gradient Descent
Comments 15 pages, 3 figures, preprint, To appear in Proceedings of ICML 2022
Why the Rich Get Richer? On the Balancedness of Random Partition Models
Comments Accepted to 2022 International Conference on Machine Learning (ICML 2022)
Approximate Bayesian Computation with Domain Expert in the Loop
Comments Accepted for publication at ICML 2022. Code available at https://github.com/lfilstro/HITL-ABC
Improving Out-of-Distribution Robustness via Selective Augmentation
Comments Accepted by ICML 2022
Discrete Probabilistic Inverse Optimal Transport
Comments ICML 2022
Controlling Conditional Language Models without Catastrophic Forgetting
Comments ICML 2022
Faster Algorithms for Learning Convex Functions
Comments 21 pages, 3 figures. Proceedings of the 39 th International Conference on Machine Learning, Baltimore, Maryland, USA, PMLR 162, 2022. Copy- right 2022 by the author(s)
Divergence-Regularized Multi-Agent Actor-Critic
Comments ICML 2022, 24 pages, 10 figures
Supervised Off-Policy Ranking
Comments Accepted by ICML 2022
Preconditioning for Scalable Gaussian Process Hyperparameter Optimization
Comments International Conference on Machine Learning (ICML)
FedScale: Benchmarking Model and System Performance of Federated Learning at Scale
Journal ref ICML (2022)
Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systems
Comments Accepted by Proceedings of the 39th International Conference on Machine Learning
