When Are Linear Stochastic Bandits Attackable?
Comments 27 pages, 3 figures, ICML 2022
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Training Novices: The Role of Human-AI Collaboration and Knowledge Transfer
Comments This is a workshop paper: Workshop on Human-Machine Collaboration and Teaming (HM-CaT 2022). The 39th International Conference on Machine Learning. Link to the workshop: https://icml.cc/Conferences/2022/Schedule?showEvent=13478
Scalable MCMC Sampling for Nonsymmetric Determinantal Point Processes
Comments ICML 2022
Risk Perspective Exploration in Distributional Reinforcement Learning
Comments ICML 2022 Workshop (AI for Agent Based Modelling)
A Human-Centric Assessment Framework for AI
Comments Accepted as submission to ICML 2022 Workshop on Human-Machine Collaboration and Teaming
Learning Symmetric Embeddings for Equivariant World Models
Comments ICML 2022
Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models
Comments ICML 2022
Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning
Comments Accepted at ICML 2022 Long presentation
A Convergent and Dimension-Independent Min-Max Optimization Algorithm
Comments This is the full version of a paper accepted for presentation in ICML 2022. The code is available at https://github.com/vijaykeswani/Min-Max-Optimization-Algorithm
Learning Iterative Reasoning through Energy Minimization
Comments ICML 2022. Website at https://energy-based-model.github.io/iterative-reasoning-as-energy-minimization/
Understanding Instance-Level Impact of Fairness Constraints
Comments 17 pages, 6 figures, ICML 2022
Improving Ensemble Distillation With Weight Averaging and Diversifying Perturbation
Comments ICML 2022
GSCLIP : A Framework for Explaining Distribution Shifts in Natural Language
Comments Accepted by ICML 2022 DataPerf
Universal and data-adaptive algorithms for model selection in linear contextual bandits
Comments 30 pages, to appear in ICML 2022
Self-supervised Learning with Random-projection Quantizer for Speech Recognition
Comments ICML 2022
Model-Value Inconsistency as a Signal for Epistemic Uncertainty
Comments The first three authors contributed equally. Accepted at ICML 2022
Interventional Contrastive Learning with Meta Semantic Regularizer
Comments Accepted by ICML 2022
Cut Inner Layers: A Structured Pruning Strategy for Efficient U-Net GANs
Comments ICML Workshop on Hardware Aware Efficient Training, 2022
NERDA-Con: Extending NER models for Continual Learning -- Integrating Distinct Tasks and Updating Distribution Shifts
Comments 6 pages, 4 figures, Accepted at Workshop on Updatable Machine Learning(UpML), International Conference on Machine Learning (ICML'22)
Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?
Comments ICML 2022; 27 pages
Optimization-Induced Graph Implicit Nonlinear Diffusion
Comments 14 pages, 3 figures. Accepted by ICML 2022. Our code is available at https://github.com/7qchen/GIND
Hardness and Algorithms for Robust and Sparse Optimization
Comments ICML 2022
On the Difficulty of Defending Self-Supervised Learning against Model Extraction
Comments Accepted at ICML 2022
Overcoming Oscillations in Quantization-Aware Training
Comments Published as oral paper at ICML 2022
Training OOD Detectors in their Natural Habitats
Comments Accepted to International Conference on Machine Learning (ICML) 2022
Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error
Comments ICML 2022
Matching Learned Causal Effects of Neural Networks with Domain Priors
Comments Accepted at International Conference on Machine Learning (ICML'22)
Order Constraints in Optimal Transport
Comments To appear in Proceedings of ICML 2022. Main Paper + Supplementary
How to Steer Your Adversary: Targeted and Efficient Model Stealing Defenses with Gradient Redirection
Comments ICML 2022
Sublinear-Time Clustering Oracle for Signed Graphs
Comments To appear at ICML'22
