Network Augmentation for Tiny Deep Learning
Comments ICLR 2022
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
An Unconstrained Layer-Peeled Perspective on Neural Collapse
Comments Published as a conference paper at ICLR 2022
Hindsight Foresight Relabeling for Meta-Reinforcement Learning
Comments ICLR 2022 camera-ready
NASI: Label- and Data-agnostic Neural Architecture Search at Initialization
Comments Published as a conference paper at ICLR 2022
Sampling with Mirrored Stein Operators
Comments ICLR 2022; Source code: https://github.com/thjashin/mirror-stein-samplers
Steerable Partial Differential Operators for Equivariant Neural Networks
Comments Published at ICLR 2022, code available at https://github.com/ejnnr/steerable_pdos
Anytime Dense Prediction with Confidence Adaptivity
Comments Published in ICLR 2022
On Feature Learning in Neural Networks with Global Convergence Guarantees
Comments Accepted by the 10th International Conference on Learning Representations (ICLR 2022)
The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models
Comments Published at ICLR 2022
Emergent Communication for Understanding Human Language Evolution: What's Missing?
Comments Published as a workshop paper at EmeCom at ICLR 2022
Uncertainty Modeling for Out-of-Distribution Generalization
Comments Accepted by ICLR 2022
Fast AdvProp
Comments ICLR 2022 camera ready version
yosm: A new yoruba sentiment corpus for movie reviews
Comments Accepted to AfricaNLP Workshop @ICLR 2022
Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiation
Comments 41 pages, 19 figures, 15 tables; minor CIFAR-10 normalisation updates from ICLR 2022 camera-ready version
On the Certified Robustness for Ensemble Models and Beyond
Comments ICLR 2022. 51 pages, 10 pages for main text. Forum and code: https://openreview.net/forum?id=tUa4REjGjTf
Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interface
Journal ref ICLR 2022
Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective
Comments 26 pages
Journal ref ICLR 2022
Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data
Comments Published at ICLR 2021
Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data
Comments ICLR 2021 (Reprint)
A Brief Guide to Designing and Evaluating Human-Centered Interactive Machine Learning
Comments 7 pages, 1 figure, Published at ML Evaluation Standards Workshop at ICLR 2022. arXiv admin note: substantial text overlap with arXiv:1905.06289
Simplicial Attention Networks
Comments Accepted to the ICLR 2022 Workshop on Geometrical and Topological Representation Learning
Scalable Sampling for Nonsymmetric Determinantal Point Processes
Comments ICLR 2022
Hierarchical Variational Memory for Few-shot Learning Across Domains
Comments 17 pages, 5 figures
Journal ref ICLR 2022
Focus on the Common Good: Group Distributional Robustness Follows
Comments Presented at ICLR 2022; Code can be found at: https://github.com/vihari/cgd
Stochastic Training is Not Necessary for Generalization
Comments 25 pages, 6 figures. Code published at github.com/JonasGeiping/fullbatchtraining. Decompressed version of paper published at ICLR 2022
COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation
Comments 24 pages, 6 figures, Accepted at ICLR 2022 (spotlight)
Learning heuristics for A*
Comments 7 pages, 2 figures. To appear at the ICLR 2022 GroundedML Workshop
INFOrmation Prioritization through EmPOWERment in Visual Model-Based RL
Comments Published in International Conference on Learning Representations (ICLR 2022)
Step-unrolled Denoising Autoencoders for Text Generation
Comments Accepted to ICLR 2022
An Exploration of Learnt Representations of W Jets
Comments Published version, to appear in ICLR workshop Deep Generative Models for Highly Structured Data. Additional appendices
