EVGen: Adversarial Networks for Learning Electric Vehicle Charging Loads and Hidden Representations
Comments Tackling Climate Change with Machine Learning Workshop at International Conference on Machine Learning (ICML) 2021
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Membership Inference Attacks on Lottery Ticket Networks
Journal ref ICML 2021 workshop on A Blessing in Disguise:The Prospects and Perils of Adversarial Machine Learning
Model-Based Reinforcement Learning via Latent-Space Collocation
Comments International Conference on Machine Learning (ICML), 2021. Videos and code at https://orybkin.github.io/latco/
Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning
Comments International Conference on Machine Learning, PMLR 139, 2021
Latent Programmer: Discrete Latent Codes for Program Synthesis
Comments ICML 2021; 15 pages, 9 figures
Distilling the Knowledge from Conditional Normalizing Flows
Comments ICML Workshop: INNF+2021
Pseudo-Rehearsal for Continual Learning with Normalizing Flows
Comments A preliminary unpublished version of this work was presented in the LifelongML workshop, at ICML 2020
Learning Task Agnostic Skills with Data-driven Guidance
Comments ICML 2021 Workshop on Unsupervised Reinforcement Learning (https://openreview.net/forum?id=CPh9DeHv08U)
Differentially private training of neural networks with Langevin dynamics for calibrated predictive uncertainty
Comments Accepted to the ICML 2021 Theory and Practice of Differential Privacy Workshop
Fast Estimation Method for the Stability of Ensemble Feature Selectors
Comments 7 pages. Supplementary material 9 pages. Accepted in ICML2021 Workshop, Subset Selection in Machine Learning: From Theory to Practice (SubSetML) URL: https://sites.google.com/view/icml-2021-subsetml
Automated Identification of Climate Risk Disclosures in Annual Corporate Reports
Comments Presented at the Tackling Climate Change with Machine Learning Workshop at ICML 2021
Computing the Newton-step faster than Hessian accumulation
Comments Presented at the Beyond First-order Methods workshop, ICML '21
Near-optimal Algorithms for Explainable k-Medians and k-Means
Comments 29 pages, 4 figures, ICML 2021
Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment
Comments Accepted @ ICML 2021; Spotlight @ ICLR 2021 "Self-Supervision for Reinforcement Learning Workshop"
Constrained Shortest Path Search with Graph Convolutional Neural Networks
Journal ref AAAI - ICML / IJCAI / AAMAS 2018 Workshop on Planning and Learning (PAL-18). Stockholm, Sweden 2018
Pure Exploration and Regret Minimization in Matching Bandits
Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139, 2021
Controlling Weather Field Synthesis Using Variational Autoencoders
Comments ICML Climate Change AI Workshop
Attend2Pack: Bin Packing through Deep Reinforcement Learning with Attention
Comments Reinforcement Learning for Real Life (RL4RealLife) Workshop in the 38th International Conference on Machine Learning, 2021
Deep Generative Learning via Schrödinger Bridge
Journal ref ICML, 2021
Randomization does not imply unconfoundedness
Comments Presented at The Neglected Assumptions in Causal Inference Workshop @ ICML 2021 ( https://sites.google.com/view/naci2021/ )
Characterizing the Generalization Error of Gibbs Algorithm with Symmetrized KL information
Comments The first and second author have contributed equally to the paper. This paper is accepted in the ICML-21 Workshop on Information-Theoretic Methods for Rigorous, Responsible, and Reliable Machine Learning: https://sites.google.com/view/itr3/schedule
Implicit Rate-Constrained Optimization of Non-decomposable Objectives
Comments ICML 2021; Code available at https://github.com/google-research/google-research/tree/master/implicit_constrained_optimization
Interpretable Machine Learning: Moving From Mythos to Diagnostics
Comments Presented at ICML HILL Workshop 2021
A Tale of Two Efficient and Informative Negative Sampling Distributions
Comments Published at ICML 2021
Doing Great at Estimating CATE? On the Neglected Assumptions in Benchmark Comparisons of Treatment Effect Estimators
Comments Workshop on the Neglected Assumptions in Causal Inference at the International Conference on Machine Learning (ICML), 2021
Bayesian Autoencoders: Analysing and Fixing the Bernoulli likelihood for Out-of-Distribution Detection
Comments Presented at the ICML 2020 Workshop on Uncertainty and Ro-bustness in Deep Learning
A Tale Of Two Long Tails
Comments Preliminary results accepted to Workshop on Uncertainty and Robustness in Deep Learning (UDL), ICML, 2021
Incentivizing Compliance with Algorithmic Instruments
Comments In Proceedings of the Thirty-eighth International Conference on Machine Learning (ICML 2021), 17 pages of main text, 53 pages total, 3 figures
Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation
Comments All data collected throughout this study, plus the code to reproduce our analysis and ANTT are available at https://github.com/microsoft/NTT
Journal ref Proceedings of the 38th International Conference on Machine Learning (ICML), 139:2644-2653, 2021
To Trust or Not to Trust a Regressor: Estimating and Explaining Trustworthiness of Regression Predictions
Comments Accepted to ICML 2021 Workshop on Human in the Loop Learning (HILL)
