Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCID10th ICLR 2022: Virtual Event
- The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net 2022
Oral Presentations
- Sabri Eyuboglu, Maya Varma, Khaled Kamal Saab, Jean-Benoit Delbrouck, Christopher Lee-Messer, Jared Dunnmon, James Zou, Christopher Ré:
Domino: Discovering Systematic Errors with Cross-Modal Embeddings. - Evan Hernandez, Sarah Schwettmann, David Bau, Teona Bagashvili, Antonio Torralba, Jacob Andreas:
Natural Language Descriptions of Deep Visual Features. - Lixu Wang, Shichao Xu, Ruiqi Xu, Xiao Wang, Qi Zhu:
Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization. - Meng Qu, Huiyu Cai, Jian Tang:
Neural Structured Prediction for Inductive Node Classification. - Asiri Wijesinghe, Qing Wang:
A New Perspective on "How Graph Neural Networks Go Beyond Weisfeiler-Lehman?". - Chulhee Yun, Shashank Rajput, Suvrit Sra:
Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond. - Yifei Wang, Jonathan Lacotte, Mert Pilanci:
The Hidden Convex Optimization Landscape of Regularized Two-Layer ReLU Networks: an Exact Characterization of Optimal Solutions. - Yonathan Efroni, Dipendra Misra, Akshay Krishnamurthy, Alekh Agarwal, John Langford:
Provably Filtering Exogenous Distractors using Multistep Inverse Dynamics. - Sebastian Flennerhag, Yannick Schroecker, Tom Zahavy, Hado van Hasselt, David Silver, Satinder Singh:
Bootstrapped Meta-Learning. - Anirudh Goyal, Aniket Rajiv Didolkar, Alex Lamb, Kartikeya Badola, Nan Rosemary Ke, Nasim Rahaman, Jonathan Binas, Charles Blundell, Michael Curtis Mozer, Yoshua Bengio:
Coordination Among Neural Modules Through a Shared Global Workspace. - Minghao Guo, Veronika Thost, Beichen Li, Payel Das, Jie Chen, Wojciech Matusik:
Data-Efficient Graph Grammar Learning for Molecular Generation. - Nicholas Carlini, Andreas Terzis:
Poisoning and Backdooring Contrastive Learning. - X. Y. Han, Vardan Papyan, David L. Donoho:
Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path. - Shuxiao Chen, Koby Crammer, Hangfeng He, Dan Roth, Weijie J. Su:
Weighted Training for Cross-Task Learning. - Marine Schimel, Ta-Chu Kao, Kristopher T. Jensen, Guillaume Hennequin:
iLQR-VAE : control-based learning of input-driven dynamics with applications to neural data. - Shiori Sagawa, Pang Wei Koh, Tony Lee, Irena Gao, Sang Michael Xie, Kendrick Shen, Ananya Kumar, Weihua Hu, Michihiro Yasunaga, Henrik Marklund, Sara Beery, Etienne David, Ian Stavness, Wei Guo
, Jure Leskovec, Kate Saenko, Tatsunori Hashimoto, Sergey Levine, Chelsea Finn, Percy Liang:
Extending the WILDS Benchmark for Unsupervised Adaptation. - S. Chandra Mouli, Bruno Ribeiro:
Asymmetry Learning for Counterfactually-invariant Classification in OOD Tasks. - Shengjia Zhao, Abhishek Sinha, Yutong He, Aidan Perreault, Jiaming Song, Stefano Ermon:
Comparing Distributions by Measuring Differences that Affect Decision Making. - Yusong Wu, Ethan Manilow, Yi Deng, Rigel Swavely, Kyle Kastner, Tim Cooijmans, Aaron C. Courville, Cheng-Zhi Anna Huang, Jesse H. Engel:
MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling. - Bo Wan, Wenjuan Han, Zilong Zheng, Tinne Tuytelaars:
Unsupervised Vision-Language Grammar Induction with Shared Structure Modeling. - Haobo Wang, Ruixuan Xiao, Yixuan Li, Lei Feng, Gang Niu, Gang Chen, Junbo Zhao:
PiCO: Contrastive Label Disambiguation for Partial Label Learning. - Shizhan Liu, Hang Yu, Cong Liao, Jianguo Li, Weiyao Lin, Alex X. Liu, Schahram Dustdar:
Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting. - Floris Geerts, Juan L. Reutter:
Expressiveness and Approximation Properties of Graph Neural Networks. - Steeven Janny, Fabien Baradel, Natalia Neverova, Madiha Nadri, Greg Mori, Christian Wolf:
Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel Space. - Hangbo Bao, Li Dong, Songhao Piao, Furu Wei:
BEiT: BERT Pre-Training of Image Transformers. - Ananya Kumar, Aditi Raghunathan, Robbie Matthew Jones, Tengyu Ma, Percy Liang:
Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution. - Zongze Wu, Yotam Nitzan, Eli Shechtman, Dani Lischinski:
StyleAlign: Analysis and Applications of Aligned StyleGAN Models. - Kohei Miyaguchi, Takayuki Katsuki, Akira Koseki, Toshiya Iwamori:
Variational Inference for Discriminative Learning with Generative Modeling of Feature Incompletion. - Albert Gu, Karan Goel, Christopher Ré:
Efficiently Modeling Long Sequences with Structured State Spaces. - Xuechen Li, Florian Tramèr, Percy Liang, Tatsunori Hashimoto:
Large Language Models Can Be Strong Differentially Private Learners. - Minkai Xu, Lantao Yu, Yang Song, Chence Shi, Stefano Ermon, Jian Tang:
GeoDiff: A Geometric Diffusion Model for Molecular Conformation Generation. - Omri Puny, Matan Atzmon, Edward J. Smith, Ishan Misra, Aditya Grover, Heli Ben-Hamu, Yaron Lipman:
Frame Averaging for Invariant and Equivariant Network Design. - Alex Rogozhnikov:
Einops: Clear and Reliable Tensor Manipulations with Einstein-like Notation. - Olivia Wiles, Sven Gowal, Florian Stimberg, Sylvestre-Alvise Rebuffi, Ira Ktena, Krishnamurthy Dvijotham, Ali Taylan Cemgil:
A Fine-Grained Analysis on Distribution Shift. - Sagar Vaze, Kai Han, Andrea Vedaldi, Andrew Zisserman:
Open-Set Recognition: A Good Closed-Set Classifier is All You Need. - Rachid Riad, Olivier Teboul, David Grangier, Neil Zeghidour:
Learning Strides in Convolutional Neural Networks. - Jake Topping, Francesco Di Giovanni, Benjamin Paul Chamberlain, Xiaowen Dong, Michael M. Bronstein:
Understanding over-squashing and bottlenecks on graphs via curvature. - Vadim Popov, Ivan Vovk, Vladimir Gogoryan, Tasnima Sadekova, Mikhail Sergeevich Kudinov, Jiansheng Wei:
Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme. - Shuming Kong, Yanyan Shen, Linpeng Huang:
Resolving Training Biases via Influence-based Data Relabeling. - Divyam Madaan, Jaehong Yoon, Yuanchun Li, Yunxin Liu, Sung Ju Hwang:
Representational Continuity for Unsupervised Continual Learning. - Kyle Hsu, Moo Jin Kim, Rafael Rafailov, Jiajun Wu, Chelsea Finn:
Vision-Based Manipulators Need to Also See from Their Hands. - Huaxiu Yao, Linjun Zhang, Chelsea Finn:
Meta-Learning with Fewer Tasks through Task Interpolation. - Huiqi Deng, Qihan Ren, Hao Zhang, Quanshi Zhang:
Discovering and Explaining the Representation Bottleneck of DNNS. - António Farinhas, Wilker Aziz, Vlad Niculae, André F. T. Martins:
Sparse Communication via Mixed Distributions. - Jason Wei, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M. Dai, Quoc V. Le:
Finetuned Language Models are Zero-Shot Learners. - Qing Jin, Jian Ren, Richard Zhuang, Sumant Hanumante, Zhengang Li, Zhiyu Chen, Yanzhi Wang, Kaiyuan Yang, Sergey Tulyakov:
F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization. - Ye Yuan, Yuda Song, Zhengyi Luo, Wen Sun, Kris M. Kitani:
Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design. - Boris N. Oreshkin, Florent Bocquelet, Félix G. Harvey, Bay Raitt, Dominic Laflamme:
ProtoRes: Proto-Residual Network for Pose Authoring via Learned Inverse Kinematics. - Nicolas Papernot, Thomas Steinke:
Hyperparameter Tuning with Renyi Differential Privacy. - Mia Chiquier, Chengzhi Mao, Carl Vondrick:
Real-Time Neural Voice Camouflage. - Shoufa Chen, Enze Xie, Chongjian Ge, Runjian Chen, Ding Liang, Ping Luo:
CycleMLP: A MLP-like Architecture for Dense Prediction. - Fan Bao, Chongxuan Li, Jun Zhu, Bo Zhang:
Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models. - Pingchuan Ma, Tao Du, Joshua B. Tenenbaum, Wojciech Matusik, Chuang Gan:
RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimation. - Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine:
The Information Geometry of Unsupervised Reinforcement Learning. - Rose E. Wang, Esin Durmus, Noah D. Goodman, Tatsunori Hashimoto:
Language modeling via stochastic processes.
Poster Presentations
- Chen Jin, Ryutaro Tanno, Thomy Mertzanidou, Eleftheria Panagiotaki, Daniel C. Alexander:
Learning to Downsample for Segmentation of Ultra-High Resolution Images. - Rasmus Berg Palm, Miguel González Duque, Shyam Sudhakaran, Sebastian Risi:
Variational Neural Cellular Automata. - Todor Davchev, Oleg Olegovich Sushkov, Jean-Baptiste Regli, Stefan Schaal, Yusuf Aytar, Markus Wulfmeier, Jon Scholz:
Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation. - Ofir Lindenbaum, Moshe Salhov, Amir Averbuch, Yuval Kluger:
L0-Sparse Canonical Correlation Analysis. - Sheikh Shams Azam, Seyyedali Hosseinalipour, Qiang Qiu, Christopher G. Brinton:
Recycling Model Updates in Federated Learning: Are Gradient Subspaces Low-Rank? - Yao Ma, Xiaorui Liu, Neil Shah, Jiliang Tang:
Is Homophily a Necessity for Graph Neural Networks? - Qizhang Feng, Ninghao Liu, Fan Yang, Ruixiang Tang, Mengnan Du, Xia Hu:
DEGREE: Decomposition Based Explanation for Graph Neural Networks. - Rob Brekelmans, Sicong Huang, Marzyeh Ghassemi, Greg Ver Steeg, Roger Baker Grosse, Alireza Makhzani:
Improving Mutual Information Estimation with Annealed and Energy-Based Bounds. - Xueyuan She, Saurabh Dash, Saibal Mukhopadhyay:
Sequence Approximation using Feedforward Spiking Neural Network for Spatiotemporal Learning: Theory and Optimization Methods. - Ravikumar Balakrishnan, Tian Li, Tianyi Zhou, Nageen Himayat, Virginia Smith, Jeff A. Bilmes:
Diverse Client Selection for Federated Learning via Submodular Maximization. - Da Xu, Yuting Ye, Chuanwei Ruan, Evren Körpeoglu, Sushant Kumar, Kannan Achan:
From Intervention to Domain Transportation: A Novel Perspective to Optimize Recommendation. - Alexey Zakharov, Qinghai Guo, Zafeirios Fountas:
Variational Predictive Routing with Nested Subjective Timescales. - Jia Guo, Jiankang Deng, Alexandros Lattas, Stefanos Zafeiriou:
Sample and Computation Redistribution for Efficient Face Detection. - Yinfeng Yu, Wenbing Huang, Fuchun Sun, Changan Chen, Yikai Wang, Xiaohong Liu:
Sound Adversarial Audio-Visual Navigation. - Aahlad Manas Puli, Lily H. Zhang, Eric Karl Oermann, Rajesh Ranganath:
Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlations. - Junfeng Guo, Ang Li, Cong Liu:
AEVA: Black-box Backdoor Detection Using Adversarial Extreme Value Analysis. - Kirby Banman, Liam Peet-Pare, Nidhi Hegde, Alona Fyshe, Martha White:
Resonance in Weight Space: Covariate Shift Can Drive Divergence of SGD with Momentum. - Chirag Gupta, Aaditya Ramdas:
Top-label calibration and multiclass-to-binary reductions. - Gabriel Mel, Jeffrey Pennington:
Anisotropic Random Feature Regression in High Dimensions. - Harshavardhan Kamarthi, Alexander Rodríguez, B. Aditya Prakash:
Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future. - Alberto Bietti:
Approximation and Learning with Deep Convolutional Models: a Kernel Perspective. - Dhruv Shah, Peng Xu, Yao Lu, Ted Xiao, Alexander Toshev, Sergey Levine, Brian Ichter:
Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning. - Raphael A. Meyer, Cameron Musco, Christopher Musco, David P. Woodruff, Samson Zhou:
Fast Regression for Structured Inputs. - Kensen Shi, Hanjun Dai, Kevin Ellis, Charles Sutton:
CrossBeam: Learning to Search in Bottom-Up Program Synthesis. - Seng Pei Liew, Tsubasa Takahashi, Michihiko Ueno:
PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning. - Michelle Miller, SueYeon Chung, Kenneth D. Miller:
Divisive Feature Normalization Improves Image Recognition Performance in AlexNet. - Benjamin LeBrun, Alessandro Sordoni, Timothy J. O'Donnell:
Evaluating Distributional Distortion in Neural Language Modeling. - Ahmed Imtiaz Humayun, Randall Balestriero, Richard G. Baraniuk:
MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining. - Pan Xu, Zheng Wen, Handong Zhao, Quanquan Gu:
Neural Contextual Bandits with Deep Representation and Shallow Exploration. - Siyan Liu, Pei Zhang, Dan Lu, Guannan Zhang:
PI3NN: Out-of-distribution-aware Prediction Intervals from Three Neural Networks. - Yingzhen Yang, Ping Li:
Discriminative Similarity for Data Clustering. - Yuqing Du, Pieter Abbeel, Aditya Grover:
It Takes Four to Tango: Multiagent Self Play for Automatic Curriculum Generation. - Fan Wu, Linyi Li, Zijian Huang, Yevgeniy Vorobeychik, Ding Zhao, Bo Li:
CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing. - Liming Pan, Cheng Shi, Ivan Dokmanic:
Neural Link Prediction with Walk Pooling. - Yihan Wang, Zhouxing Shi, Quanquan Gu, Cho-Jui Hsieh:
On the Convergence of Certified Robust Training with Interval Bound Propagation. - Yu Meng, Chenyan Xiong, Payal Bajaj, Saurabh Tiwary, Paul N. Bennett, Jiawei Han, Xia Song:
Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators. - Anuroop Sriram, Abhishek Das, Brandon M. Wood, Siddharth Goyal, C. Lawrence Zitnick:
Towards Training Billion Parameter Graph Neural Networks for Atomic Simulations. - Chenjun Xiao, Bo Dai, Jincheng Mei, Oscar A Ramirez, Ramki Gummadi, Chris Harris, Dale Schuurmans:
Understanding and Leveraging Overparameterization in Recursive Value Estimation. - Khashayar Gatmiry, Stefanie Jegelka, Jonathan A. Kelner:
Optimization and Adaptive Generalization of Three layer Neural Networks. - Ruibo Liu, Chongyang Gao, Chenyan Jia, Guangxuan Xu, Soroush Vosoughi:
Non-Parallel Text Style Transfer with Self-Parallel Supervision. - Quanfu Fan, Chun-Fu Chen, Rameswar Panda:
Can an Image Classifier Suffice For Action Recognition? - Wei Deng, Siqi Liang, Botao Hao, Guang Lin, Faming Liang:
Interacting Contour Stochastic Gradient Langevin Dynamics. - Siqi Liu, Luke Marris, Daniel Hennes, Josh Merel, Nicolas Heess, Thore Graepel:
NeuPL: Neural Population Learning. - Minghao Han, Jacob Euler-Rolle, Robert K. Katzschmann:
DeSKO: Stability-Assured Robust Control with a Deep Stochastic Koopman Operator. - Panagiotis Misiakos, Georgios Smyrnis, George Retsinas, Petros Maragos:
Neural Network Approximation based on Hausdorff distance of Tropical Zonotopes. - Xiong Zhou, Xianming Liu, Deming Zhai, Junjun Jiang, Xin Gao, Xiangyang Ji:
Learning Towards The Largest Margins. - Yonggan Fu, Shunyao Zhang, Shang Wu, Cheng Wan, Yingyan Lin:
Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations? - David Berthelot, Rebecca Roelofs, Kihyuk Sohn, Nicholas Carlini, Alexey Kurakin:
AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation. - Claudio Ferrari, Mark Niklas Müller, Nikola Jovanovic, Martin T. Vechev:
Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound. - Daniel Watson, William Chan, Jonathan Ho, Mohammad Norouzi:
Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Quality. - Abhishek Shetty, Raaz Dwivedi, Lester Mackey:
Distribution Compression in Near-Linear Time. - Frank F. Xu, Junxian He, Graham Neubig, Vincent Josua Hellendoorn:
Capturing Structural Locality in Non-parametric Language Models. - Shaojin Ding, Tianlong Chen, Zhangyang Wang:
Audio Lottery: Speech Recognition Made Ultra-Lightweight, Noise-Robust, and Transferable. - Georgios Georgakis, Bernadette Bucher, Karl Schmeckpeper, Siddharth Singh, Kostas Daniilidis:
Learning to Map for Active Semantic Goal Navigation. - Danijar Hafner:
Benchmarking the Spectrum of Agent Capabilities. - Peihao Zhu, Rameen Abdal, John Femiani, Peter Wonka:
Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks. - Rylee Thompson, Boris Knyazev, Elahe Ghalebi, Jungtaek Kim, Graham W. Taylor:
On Evaluation Metrics for Graph Generative Models. - Emily Black, Klas Leino, Matt Fredrikson:
Selective Ensembles for Consistent Predictions. - Wei Jin, Lingxiao Zhao, Shichang Zhang, Yozen Liu, Jiliang Tang, Neil Shah:
Graph Condensation for Graph Neural Networks. - Yonatan Dukler, Alessandro Achille, Giovanni Paolini, Avinash Ravichandran, Marzia Polito, Stefano Soatto:
DIVA: Dataset Derivative of a Learning Task. - Baihe Huang, Jason D. Lee, Zhaoran Wang, Zhuoran Yang:
Towards General Function Approximation in Zero-Sum Markov Games. - Kartik Goyal, Chris Dyer, Taylor Berg-Kirkpatrick:
Exposing the Implicit Energy Networks behind Masked Language Models via Metropolis--Hastings. - Victor Schmidt, Alexandra Luccioni, Mélisande Teng, Tianyu Zhang, Alexia Reynaud, Sunand Raghupathi, Gautier Cosne, Adrien Juraver, Vahe Vardanyan, Alex Hernández-García, Yoshua Bengio:
ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods. - Tracy Ke, Longlin Wang:
A Comparison of Hamming Errors of Representative Variable Selection Methods. - Gabriele Cesa, Leon Lang, Maurice Weiler:
A Program to Build E(N)-Equivariant Steerable CNNs. - Tanner Fiez, Chi Jin, Praneeth Netrapalli, Lillian J. Ratliff:
Minimax Optimization with Smooth Algorithmic Adversaries. - Xiaoyun Li, Belhal Karimi, Ping Li:
On Distributed Adaptive Optimization with Gradient Compression. - Saurabh Garg, Sivaraman Balakrishnan, Zachary Chase Lipton, Behnam Neyshabur, Hanie Sedghi:
Leveraging unlabeled data to predict out-of-distribution performance. - Yutong Wang, Clayton Scott:
VC dimension of partially quantized neural networks in the overparametrized regime. - Yangjun Ruan, Yann Dubois, Chris J. Maddison:
Optimal Representations for Covariate Shift. - Hattie Zhou, Ankit Vani, Hugo Larochelle, Aaron C. Courville:
Fortuitous Forgetting in Connectionist Networks. - Ian M. Gemp, Brian McWilliams, Claire Vernade, Thore Graepel:
EigenGame Unloaded: When playing games is better than optimizing. - Peifeng Wang, Jonathan Zamora, Junfeng Liu, Filip Ilievski, Muhao Chen, Xiang Ren:
Contextualized Scene Imagination for Generative Commonsense Reasoning. - Jiquan Ngiam, Vijay Vasudevan, Benjamin Caine, Zhengdong Zhang, Hao-Tien Lewis Chiang, Jeffrey Ling, Rebecca Roelofs, Alex Bewley, Chenxi Liu, Ashish Venugopal, David J. Weiss, Ben Sapp, Zhifeng Chen, Jonathon Shlens:
Scene Transformer: A unified architecture for predicting future trajectories of multiple agents.