The problem with DDPG: understanding failures in deterministic environments with sparse rewards
Comments 19 pages, submitted to ICLR 2020
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
How Do Vision Transformers Work?
Comments ICLR 2022 (Spotlight)
Fooling Explanations in Text Classifiers
Journal ref International Conference on Learning Representations, 2022
GradMax: Growing Neural Networks using Gradient Information
Comments ICLR 2022
Journal ref International Conference on Learning Representations, 2022
Progressive Distillation for Fast Sampling of Diffusion Models
Comments Published as a conference paper at ICLR 2022
EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction
Comments 39th International Conference on Machine Learning (ICML 2022). Also accepted at ICLR 2022 GTRL and at ICLR 2022 MLDD as spotlight
Journal ref 39th International Conference on Machine Learning (ICML 2022)
Vector-quantized Image Modeling with Improved VQGAN
Comments Accepted in ICLR 2022
Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbations
Comments Published as a conference paper at ICLR 2022
SystemMatch: optimizing preclinical drug models to human clinical outcomes via generative latent-space matching
Comments Published at the MLDD workshop, ICLR 2022
Neural Topic Model via Optimal Transport
Comments Published in ICLR 2021, link: https://openreview.net/forum?id=Oos98K9Lv-k, code: https://github.com/ethanhezhao/NeuralSinkhornTopicModel
PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling Policy and Environment Representations
Comments Accepted on IJCAI 2022 and a previous version of this work is presented at the Generalizable Policy Learning in the Physical World Workshop (ICLR 2022)
Efficient and Differentiable Conformal Prediction with General Function Classes
Comments Appearing at ICLR 2022
Policy Smoothing for Provably Robust Reinforcement Learning
Comments Published as a conference paper at ICLR 2022
Effective Abstract Reasoning with Dual-Contrast Network
Comments Published on ICLR 2021
Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap
Comments Accepeted by ICLR 2022
Rethinking ValueDice: Does It Really Improve Performance?
Comments This paper appeared at the blog track of the 10th international conference on learning representations (ICLR), 2022. Link: https://iclr-blog-track.github.io/2022/03/25/rethinking-valuedice/
Towards Creativity Characterization of Generative Models via Group-based Subset Scanning
Comments Accepted to IJCAI 2022 - Creativity Track - Extended version from Synthetic Data Generation Workshop at ICLR'21 submission (arXiv:2104.00479). arXiv admin note: text overlap with arXiv:2105.12479
Reward Uncertainty for Exploration in Preference-based Reinforcement Learning
Comments ICLR 2022. Last two authors advised equally
Label Leakage and Protection in Two-party Split Learning
Comments Accepted to ICLR 2022 (https://openreview.net/forum?id=cOtBRgsf2fO)
Learning Stabilizing Policies in Stochastic Control Systems
Comments ICLR 2022 Workshop on Socially Responsible Machine Learning (SRML)
Learning multi-scale functional representations of proteins from single-cell microscopy data
Comments ICLR MLDD 2022
Towards Continual Knowledge Learning of Language Models
Comments published at ICLR 2022
Rethinking Streaming Machine Learning Evaluation
Comments ML Evaluation Standards Workshop (ICLR 2022)
What is Your Metric Telling You? Evaluating Classifier Calibration under Context-Specific Definitions of Reliability
Comments Accepted in the ICLR 2022 Machine Learning Evaluation Standards Workshop
Manifold-aligned Neighbor Embedding
Comments Accepted at the ICLR 2022 Workshop on Geometrical and Topological Representation Learning
De novo design of protein target specific scaffold-based Inhibitors via Reinforcement Learning
Comments Published at the MLDD workshop, ICLR 2022
Learning Geometrically Disentangled Representations of Protein Folding Simulations
Comments 13 pages, appeared at SimDL ICLR Workshop 2021
Domino: Discovering Systematic Errors with Cross-Modal Embeddings
Comments ICLR 2022 (Oral)
Tasting the cake: evaluating self-supervised generalization on out-of-distribution multimodal MRI data
Comments Presented as a RobustML workshop paper at ICLR 2021
Learning latent representations for operational nitrogen response rate prediction
Comments Appeared at the AI for Earth Sciences workshop at @ICLR2022, April 29, 2022. https://ai4earthscience.github.io/iclr-2022-workshop/
