ICLR 2022

1,094 papers

Hybrid Random Features

Krzysztof Marcin Choromanski, Han Lin, Haoxian Chen, Arijit Sehanobish, Yuanzhe Ma

Goal-Directed Planning via Hindsight Experience Replay

Lorenzo Moro, Amarildo Likmeta, Enrico Prati, Marcello Restelli

Bayesian Neural Network Priors Revisited

Vincent Fortuin, Adrià Garriga-Alonso, Sebastian W. Ober, Florian Wenzel, Gunnar Rätsch

Scattering Networks on the Sphere for Scalable and Rotationally Equivariant Spherical CNNs

Jason McEwen, Christopher Wallis, Augustine N. Mavor-Parker

Space-Time Graph Neural Networks

Samar Hadou, Charilaos I Kanatsoulis, Alejandro Ribeiro

Vitruvion: A Generative Model of Parametric CAD Sketches

Ari Seff, Wenda Zhou, Nick Richardson, Ryan P Adams

Scale Efficiently: Insights from Pretraining and Finetuning Transformers

Yi Tay, Mostafa Dehghani, Jinfeng Rao, William Fedus, Samira Abnar

Conditional Object-Centric Learning from Video

Thomas Kipf, Gamaleldin Fathy Elsayed, Aravindh Mahendran, Austin Stone, Sara Sabour

Meta Learning Low Rank Covariance Factors for Energy Based Deterministic Uncertainty

Jeffrey Ryan Willette, Hae Beom Lee, Juho Lee, Sung Ju Hwang

Missingness Bias in Model Debugging

Saachi Jain, Hadi Salman, Eric Wong, Pengchuan Zhang, Vibhav Vineet

Revisiting flow generative models for Out-of-distribution detection

Dihong Jiang, Sun Sun, Yaoliang Yu

Fine-grained Differentiable Physics: A Yarn-level Model for Fabrics

Deshan Gong, Zhanxing Zhu, Andrew J. Bulpitt, He Wang

Auto-scaling Vision Transformers without Training

Wuyang Chen, Wei Huang, Xianzhi Du, Xiaodan Song, Zhangyang Wang

Autoregressive Diffusion Models

Emiel Hoogeboom, Alexey A. Gritsenko, Jasmijn Bastings, Ben Poole, Rianne van den Berg

Attacking deep networks with surrogate-based adversarial black-box methods is easy

Nicholas A. Lord, Romain Mueller, Luca Bertinetto

Defending Against Image Corruptions Through Adversarial Augmentations

Dan Andrei Calian, Florian Stimberg, Olivia Wiles, Sylvestre-Alvise Rebuffi, András György

Provable Learning-based Algorithm For Sparse Recovery

Xinshi Chen, Haoran Sun, Le Song

MoReL: Multi-omics Relational Learning

Arman Hasanzadeh, Ehsan Hajiramezanali, Nick Duffield, Xiaoning Qian

GLASS: GNN with Labeling Tricks for Subgraph Representation Learning

Xiyuan Wang, Muhan Zhang

Information Bottleneck: Exact Analysis of (Quantized) Neural Networks

Stephan Sloth Lorenzen, Christian Igel, Mads Nielsen

Dealing with Non-Stationarity in MARL via Trust-Region Decomposition

Wenhao Li, Xiangfeng Wang, Bo Jin, Junjie Sheng, Hongyuan Zha

Information-theoretic Online Memory Selection for Continual Learning

Shengyang Sun, Daniele Calandriello, Huiyi Hu, Ang Li, Michalis Titsias

On the Role of Neural Collapse in Transfer Learning

Tomer Galanti, András György, Marcus Hutter

Self-Supervised Inference in State-Space Models

David Ruhe, Patrick Forré

Generalization Through the Lens of Leave-One-Out Error

Gregor Bachmann, Thomas Hofmann, Aurelien Lucchi

Learning Scenario Representation for Solving Two-stage Stochastic Integer Programs

Yaoxin Wu, Wen Song, Zhiguang Cao, Jie Zhang

Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation

Junhyun Nam, Jaehyung Kim, Jaeho Lee, Jinwoo Shin

Convergent Graph Solvers

Junyoung Park, Jinhyun Choo, Jinkyoo Park

SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning

Jongjin Park, Younggyo Seo, Jinwoo Shin, Honglak Lee, Pieter Abbeel

Surreal-GAN:Semi-Supervised Representation Learning via GAN for uncovering heterogeneous disease-related imaging patterns

Zhijian Yang, Junhao Wen, Christos Davatzikos

Towards Continual Knowledge Learning of Language Models

Joel Jang, Seonghyeon Ye, Sohee Yang, Joongbo Shin, Janghoon Han

Equivariant Graph Mechanics Networks with Constraints

Wenbing Huang, Jiaqi Han, Yu Rong, Tingyang Xu, Fuchun Sun

Continual Normalization: Rethinking Batch Normalization for Online Continual Learning

Quang Pham, Chenghao Liu, Steven Hoi

Online Ad Hoc Teamwork under Partial Observability

Pengjie Gu, Mengchen Zhao, Jianye Hao, Bo An

Nonlinear ICA Using Volume-Preserving Transformations

Xiaojiang Yang, Yi Wang, Jiacheng Sun, Xing Zhang, Shifeng Zhang

PF-GNN: Differentiable particle filtering based approximation of universal graph representations

Mohammed Haroon Dupty, Yanfei Dong, Wee Sun Lee

Topologically Regularized Data Embeddings

Robin Vandaele, Bo Kang, Jefrey Lijffijt, Tijl De Bie, Yvan Saeys

Rethinking Goal-Conditioned Supervised Learning and Its Connection to Offline RL

Rui Yang, Yiming Lu, Wenzhe Li, Hao Sun, Meng Fang

Discovering Nonlinear PDEs from Scarce Data with Physics-encoded Learning

Chengping Rao, Pu Ren, Yang Liu, Hao Sun

Proving the Lottery Ticket Hypothesis for Convolutional Neural Networks

Arthur da Cunha, Emanuele Natale, Laurent Viennot

Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbations

Jinyuan Jia, Binghui Wang, Xiaoyu Cao, Hongbin Liu, Neil Zhenqiang Gong

QUERY EFFICIENT DECISION BASED SPARSE ATTACKS AGAINST BLACK-BOX DEEP LEARNING MODELS

Viet Vo, Ehsan M Abbasnejad, Damith Ranasinghe

Parallel Training of GRU Networks with a Multi-Grid Solver for Long Sequences

Euhyun Moon, Eric C Cyr

Knowledge Infused Decoding

Ruibo Liu, Guoqing Zheng, Shashank Gupta, Radhika Gaonkar, Chongyang Gao

Toward Efficient Low-Precision Training: Data Format Optimization and Hysteresis Quantization

Sunwoo Lee, Jeongwoo Park, Dongsuk Jeon

Structure-Aware Transformer Policy for Inhomogeneous Multi-Task Reinforcement Learning

Sunghoon Hong, Deunsol Yoon, Kee-eung Kim

Relational Surrogate Loss Learning

Tao Huang, Zekang Li, Hua Lu, Yong Shan, Shusheng Yang

Sqrt(d) Dimension Dependence of Langevin Monte Carlo

Ruilin Li, Hongyuan Zha, Molei Tao

Anti-Concentrated Confidence Bonuses For Scalable Exploration

Jordan T. Ash, Cyril Zhang, Surbhi Goel, Akshay Krishnamurthy, Sham M. Kakade

Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization

Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou

Understanding Intrinsic Robustness Using Label Uncertainty

Xiao Zhang, David Evans

Meta-Imitation Learning by Watching Video Demonstrations

Jiayi Li, Tao Lu, Xiaoge Cao, Yinghao Cai, Shuo Wang

A Zest of LIME: Towards Architecture-Independent Model Distances

Hengrui Jia, Hongyu Chen, Jonas Guan, Ali Shahin Shamsabadi, Nicolas Papernot

Rethinking Supervised Pre-Training for Better Downstream Transferring

Yutong Feng, Jianwen Jiang, Mingqian Tang, Rong Jin, Yue Gao

Self-Joint Supervised Learning

Navid Kardan, Mubarak Shah, Mitch Hill

Practical Integration via Separable Bijective Networks

Christopher M Bender, Patrick Emmanuel, Michael K. Reiter, Junier Oliva

OBJECT DYNAMICS DISTILLATION FOR SCENE DECOMPOSITION AND REPRESENTATION

Qu Tang, Xiangyu Zhu, Zhen Lei, Zhaoxiang Zhang

Towards Evaluating the Robustness of Neural Networks Learned by Transduction

Jiefeng Chen, Xi Wu, Yang Guo, Yingyu Liang, Somesh Jha

Generalized rectifier wavelet covariance models for texture synthesis

Antoine Brochard, Sixin Zhang, Stephane Mallat

CoMPS: Continual Meta Policy Search

Glen Berseth, Zhiwei Zhang, Grace Zhang, Chelsea Finn, Sergey Levine

Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients

Milad Alizadeh, Shyam A. Tailor, Luisa M Zintgraf, Joost van Amersfoort, Sebastian Farquhar

Overcoming The Spectral Bias of Neural Value Approximation

Ge Yang, Anurag Ajay, Pulkit Agrawal

Differentiable Expectation-Maximization for Set Representation Learning

Minyoung Kim

Domain Adversarial Training: A Game Perspective

David Acuna, Marc T Law, Guojun Zhang, Sanja Fidler

GATSBI: Generative Adversarial Training for Simulation-Based Inference

Poornima Ramesh, Jan-Matthis Lueckmann, Jan Boelts, Álvaro Tejero-Cantero, David S. Greenberg

Transfer RL across Observation Feature Spaces via Model-Based Regularization

Yanchao Sun, Ruijie Zheng, Xiyao Wang, Andrew E Cohen, Furong Huang

Stochastic Training is Not Necessary for Generalization

Jonas Geiping, Micah Goldblum, Phil Pope, Michael Moeller, Tom Goldstein

Boosting the Certified Robustness of L-infinity Distance Nets

Bohang Zhang, Du Jiang, Di He, Liwei Wang

Normalization of Language Embeddings for Cross-Lingual Alignment

Prince Osei Aboagye, YAN ZHENG, Chin-Chia Michael Yeh, Junpeng Wang, Wei Zhang

Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching

Pierre-Alexandre Kamienny, Jean Tarbouriech, Sylvain Lamprier, Alessandro Lazaric, Ludovic DENOYER

Equivariant Self-Supervised Learning: Encouraging Equivariance in Representations

Rumen Dangovski, Li Jing, Charlotte Loh, Seungwook Han, Akash Srivastava

LOSSY COMPRESSION WITH DISTRIBUTION SHIFT AS ENTROPY CONSTRAINED OPTIMAL TRANSPORT

Huan Liu, George Zhang, Jun Chen, Ashish J Khisti

Conditioning Sequence-to-sequence Networks with Learned Activations

Alberto Gil Couto Pimentel Ramos, Abhinav Mehrotra, Nicholas Donald Lane, Sourav Bhattacharya

Adversarial Retriever-Ranker for Dense Text Retrieval

Hang Zhang, Yeyun Gong, Yelong Shen, Jiancheng Lv, Nan Duan

Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interface

Tuan Anh Le, Katherine M. Collins, Luke Hewitt, Kevin Ellis, Siddharth N

The Efficiency Misnomer

Mostafa Dehghani, Yi Tay, Anurag Arnab, Lucas Beyer, Ashish Vaswani

Mapping Language Models to Grounded Conceptual Spaces

Roma Patel, Ellie Pavlick

Multi-objective Optimization by Learning Space Partition

Yiyang Zhao, Linnan Wang, Kevin Yang, Tianjun Zhang, Tian Guo

Amortized Implicit Differentiation for Stochastic Bilevel Optimization

Michael Arbel, Julien Mairal

On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications

Ziqiao Wang, Yongyi Mao

Mapping conditional distributions for domain adaptation under generalized target shift

Matthieu Kirchmeyer, Alain Rakotomamonjy, Emmanuel de Bézenac, Patrick Gallinari

On Non-Random Missing Labels in Semi-Supervised Learning

Xinting Hu, Yulei Niu, Chunyan Miao, Xian-Sheng Hua, Hanwang Zhang

LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5

Chengwei Qin, Shafiq Joty

Invariant Causal Representation Learning for Out-of-Distribution Generalization

Chaochao Lu, Yuhuai Wu, José Miguel Hernández-Lobato, Bernhard Schölkopf

The Spectral Bias of Polynomial Neural Networks

Moulik Choraria, Leello Tadesse Dadi, Grigorios Chrysos, Julien Mairal, Volkan Cevher

Top-N: Equivariant Set and Graph Generation without Exchangeability

Clément Vignac, Pascal Frossard

Procedural generalization by planning with self-supervised world models

Ankesh Anand, Jacob C Walker, Yazhe Li, Eszter Vértes, Julian Schrittwieser

IGLU: Efficient GCN Training via Lazy Updates

S Deepak Narayanan, Aditya Sinha, Prateek Jain, Purushottam Kar, SUNDARARAJAN SELLAMANICKAM

Diurnal or Nocturnal? Federated Learning of Multi-branch Networks from Periodically Shifting Distributions

Chen Zhu, Zheng Xu, Mingqing Chen, Jakub Konečný, Andrew Hard

Geometric Transformers for Protein Interface Contact Prediction

Alex Morehead, Chen Chen, Jianlin Cheng

Evaluating Disentanglement of Structured Representations

Raphaël Dang-Nhu

Neural Processes with Stochastic Attention: Paying more attention to the context dataset

Mingyu Kim, Kyeong Ryeol Go, Se-Young Yun

Robust and Scalable SDE Learning: A Functional Perspective

Scott Alexander Cameron, Tyron Luke Cameron, Arnu Pretorius, Stephen J. Roberts

Large-Scale Representation Learning on Graphs via Bootstrapping

Shantanu Thakoor, Corentin Tallec, Mohammad Gheshlaghi azar, Mehdi Azabou, Eva L Dyer

Cross-Domain Imitation Learning via Optimal Transport

Arnaud Fickinger, Samuel Cohen, Stuart Russell, Brandon Amos

A Loss Curvature Perspective on Training Instabilities of Deep Learning Models

Justin Gilmer, Behrooz Ghorbani, Ankush Garg, Sneha Kudugunta, Behnam Neyshabur

Mirror Descent Policy Optimization

Manan Tomar, Lior Shani, Yonathan Efroni, Mohammad Ghavamzadeh

Proof Artifact Co-Training for Theorem Proving with Language Models

Jesse Michael Han, Jason Rute, Yuhuai Wu, Edward Ayers, Stanislas Polu

Enabling Arbitrary Translation Objectives with Adaptive Tree Search

Wang Ling, Wojciech Stokowiec, Domenic Donato, Chris Dyer, Lei Yu

The Role of Pretrained Representations for the OOD Generalization of RL Agents

Frederik Träuble, Andrea Dittadi, Manuel Wuthrich, Felix Widmaier, Peter Vincent Gehler