Sparse Convex Optimization via Adaptively Regularized Hard Thresholding
Comments Accepted to ICML 2020
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Lifted Disjoint Paths with Application in Multiple Object Tracking
Comments ICML 2020, Codebase available at https://github.com/AndreaHor/LifT_Solver
Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimism
Comments To appear in proceedings of the 37th International Conference on Machine Learning. Shortened conference version of its journal version (available at: arXiv:1906.02922)
Inverse Active Sensing: Modeling and Understanding Timely Decision-Making
Journal ref In Proc. 37th International Conference on Machine Learning (ICML 2020)
Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case
Journal ref International Conference on Machine Learning (ICML 2020)
Uncertainty in Neural Relational Inference Trajectory Reconstruction
Comments 4 main pages, 1 page of supplementary materials. Accepted for presentation at the Graph Representation Learning and Beyond workshop at ICML 2020
Generative Adversarial Imitation Learning with Neural Networks: Global Optimality and Convergence Rate
Comments 42 pages; accepted to ICML; initial draft submitted in Feb, 2020
Two Routes to Scalable Credit Assignment without Weight Symmetry
Comments ICML 2020 Camera Ready Version, 19 pages including supplementary information, 10 figures
Aggregation of Multiple Knockoffs
Comments Accepted to ICML 2020 (Thirty-seventh International Conference on Machine Learning). This version includes both the main text of the conference paper and supplementary materials (as appendices). 35 pages, 7 figures
Multiple Imputation with Denoising Autoencoder using Metamorphic Truth and Imputation Feedback
Comments Machine Learning and Data Mining in Pattern Recognition, 16th International Conference on Machine Learning and Data Mining, MLDM 2020, Amsterdam, The Netherlands, July 20-21, 2020, Proceedings, pp. 197-208
WaveFlow: A Compact Flow-based Model for Raw Audio
Comments Published at ICML 2020. Code and pre-trained models: https://github.com/PaddlePaddle/Parakeet
Normalized Loss Functions for Deep Learning with Noisy Labels
Comments Accepted to ICML 2020
A Note on Over-Smoothing for Graph Neural Networks
Comments Appeared at ICML 2020 Graph Representation Learning workshop. https://grlplus.github.io/cfp/
On Bayesian Search for the Feasible Space Under Computationally Expensive Constraints
Comments Accepted at The Sixth International Conference on Machine Learning, Optimization, and Data Science. Main content 12 pages, a total of 19 pages with supplementary. 3 Figures and 2 tables. Python code for Bayesian search is available at: http://bitbucket.org/arahat/lod-2020
Message Passing Query Embedding
Comments Presented at ICML 2020 - GRL+ Workshop
Graphs, Entities, and Step Mixture
Comments 5 pages, 4 figures, 3 tables accepted for ICML 2020 workshop on Graph Representation Learning and Beyond (GRL+ 2020)
Journal ref ICML 2020 GRL+ workshop
From Importance Sampling to Doubly Robust Policy Gradient
Comments ICML 2020
Why bigger is not always better: on finite and infinite neural networks
Journal ref ICML 2020
On the Global Optimality of Model-Agnostic Meta-Learning
Comments 41 pages; accepted to ICML; initial draft submitted in Feb, 2020
How to train your neural ODE: the world of Jacobian and kinetic regularization
Comments Accepted to ICML 2020
Deep Coordination Graphs
Comments Accepted at ICML 2020
Hybrid Session-based News Recommendation using Recurrent Neural Networks
Comments From the Proceeding of the LatinX in AI Research (LXAI) at ICML 2020. arXiv admin note: text overlap with arXiv:1904.10367
Combinatorial Pure Exploration of Dueling Bandit
Comments Accepted to ICML 2020
Limits of Transfer Learning
Comments Accepted for presentation at the Sixth International Conference on Machine Learning, Optimization, and Data Science (LOD 2020), July 19-23, 2020
A Multiscale Graph Convolutional Network Using Hierarchical Clustering
Comments 5 pages, 2 figures, submitted as a GRL+ workshop paper for ICML 2020
Logarithmic Regret for Adversarial Online Control
Comments ICML 2020
Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers
Comments ICML 2020
Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles
Comments ICML 2020
Soft Threshold Weight Reparameterization for Learnable Sparsity
Comments 19 pages, 10 figures, Published at International Conference on Machine Learning (ICML) 2020
Learning Efficient Multi-agent Communication: An Information Bottleneck Approach
Comments ICML 2020
