ICLR 2022

1,094 papers

StyleNeRF: A Style-based 3D Aware Generator for High-resolution Image Synthesis

Jiatao Gu, Lingjie Liu, Peng Wang, Christian Theobalt

Neural Models for Output-Space Invariance in Combinatorial Problems

Yatin Nandwani, Vidit Jain, Mausam ., Parag Singla

Is Importance Weighting Incompatible with Interpolating Classifiers?

Ke Alexander Wang, Niladri Shekhar Chatterji, Saminul Haque, Tatsunori Hashimoto

How many degrees of freedom do we need to train deep networks: a loss landscape perspective

Brett W Larsen, Stanislav Fort, Nic Becker, Surya Ganguli

Relating transformers to models and neural representations of the hippocampal formation

James C. R. Whittington, Joseph Warren, Tim E.J. Behrens

Graph-less Neural Networks: Teaching Old MLPs New Tricks Via Distillation

Shichang Zhang, Yozen Liu, Yizhou Sun, Neil Shah

Permutation-Based SGD: Is Random Optimal?

Shashank Rajput, Kangwook Lee, Dimitris Papailiopoulos

Decentralized Learning for Overparameterized Problems: A Multi-Agent Kernel Approximation Approach

Prashant Khanduri, Haibo Yang, Mingyi Hong, Jia Liu, Hoi To Wai

Reward Uncertainty for Exploration in Preference-based Reinforcement Learning

Xinran Liang, Katherine Shu, Kimin Lee, Pieter Abbeel

Practical Conditional Neural Process Via Tractable Dependent Predictions

Stratis Markou, James Requeima, Wessel Bruinsma, Anna Vaughan, Richard E Turner

Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models

Liam H Fowl, Jonas Geiping, Wojciech Czaja, Micah Goldblum, Tom Goldstein

Language-biased image classification: evaluation based on semantic representations

Yoann Lemesle, Masataka Sawayama, Guillermo Valle-Pérez, Maxime Adolphe, Hélène Sauzéon

Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap

Yifei Wang, Qi Zhang, Yisen Wang, Jiansheng Yang, Zhouchen Lin

Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?

Vikash Sehwag, Saeed Mahloujifar, Tinashe Handina, Sihui Dai, Chong Xiang

A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based Model

Jianwen Xie, Yaxuan Zhu, Jun Li, Ping Li

How Did the Model Change? Efficiently Assessing Machine Learning API Shifts

Lingjiao Chen, Matei Zaharia, James Zou

Map Induction: Compositional spatial submap learning for efficient exploration in novel environments

Sugandha Sharma, Aidan Curtis, Marta Kryven, Joshua B. Tenenbaum, Ila R Fiete

High Probability Bounds for a Class of Nonconvex Algorithms with AdaGrad Stepsize

Ali Kavis, Kfir Yehuda Levy, Volkan Cevher

Collapse by Conditioning: Training Class-conditional GANs with Limited Data

Mohamad Shahbazi, Martin Danelljan, Danda Pani Paudel, Luc Van Gool

Constructing a Good Behavior Basis for Transfer using Generalized Policy Updates

Safa Alver, Doina Precup

Non-Linear Operator Approximations for Initial Value Problems

Gaurav Gupta, Xiongye Xiao, Radu Balan, Paul Bogdan

Neural Parameter Allocation Search

Bryan A. Plummer, Nikoli Dryden, Julius Frost, Torsten Hoefler, Kate Saenko

Counterfactual Plans under Distributional Ambiguity

Ngoc Bui, Duy Nguyen, Viet Anh Nguyen

Learning Distributionally Robust Models at Scale via Composite Optimization

Farzin Haddadpour, Mohammad Mahdi Kamani, Mehrdad Mahdavi, Amin Karbasi

Offline Reinforcement Learning with Implicit Q-Learning

Ilya Kostrikov, Ashvin Nair, Sergey Levine

Optimizing Neural Networks with Gradient Lexicase Selection

Li Ding, Lee Spector

The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models

Alexander Pan, Kush Bhatia, Jacob Steinhardt

Illiterate DALL-E Learns to Compose

Gautam Singh, Fei Deng, Sungjin Ahn

HTLM: Hyper-Text Pre-Training and Prompting of Language Models

Armen Aghajanyan, Dmytro Okhonko, Mike Lewis, Mandar Joshi, Hu Xu

MetaMorph: Learning Universal Controllers with Transformers

Agrim Gupta, Linxi Fan, Surya Ganguli, Li Fei-fei

Data Poisoning Won’t Save You From Facial Recognition

Evani Radiya-Dixit, Sanghyun Hong, Nicholas Carlini, Florian Tramer

The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks

Rahim Entezari, Hanie Sedghi, Olga Saukh, Behnam Neyshabur

Discovering Latent Concepts Learned in BERT

Fahim Dalvi, Abdul Rafae Khan, Firoj Alam, Nadir Durrani, Jia Xu

Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks

Benjamin Bowman, Guido Montúfar

A fast and accurate splitting method for optimal transport: analysis and implementation

Vien V. Mai, Jacob Lindbäck, Mikael Johansson

Autonomous Learning of Object-Centric Abstractions for High-Level Planning

Steven James, Benjamin Rosman, George Konidaris

MCMC Should Mix: Learning Energy-Based Model with Neural Transport Latent Space MCMC

Erik Nijkamp, Ruiqi Gao, Pavel Sountsov, Srinivas Vasudevan, Bo Pang

Imitation Learning from Observations under Transition Model Disparity

Tanmay Gangwani, Yuan Zhou, Jian Peng

Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory

Tianrong Chen, Guan-Horng Liu, Evangelos Theodorou

On the Convergence of mSGD and AdaGrad for Stochastic Optimization

ruinan Jin, Yu Xing, Xingkang He

Adaptive Wavelet Transformer Network for 3D Shape Representation Learning

Hao Huang, Yi Fang

The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program

Yifei Wang, Mert Pilanci

Fair Normalizing Flows

Mislav Balunovic, Anian Ruoss, Martin Vechev

Pareto Policy Adaptation

Panagiotis Kyriakis, Jyotirmoy Deshmukh, Paul Bogdan

Towards Empirical Sandwich Bounds on the Rate-Distortion Function

Yibo Yang, Stephan Mandt

CKConv: Continuous Kernel Convolution For Sequential Data

David W. Romero, Anna Kuzina, Erik J Bekkers, Jakub Mikolaj Tomczak, Mark Hoogendoorn

Learning Transferable Reward for Query Object Localization with Policy Adaptation

Tingfeng Li, Shaobo Han, Martin Renqiang Min, Dimitris N. Metaxas

How Attentive are Graph Attention Networks?

Shaked Brody, Uri Alon, Eran Yahav

Phenomenology of Double Descent in Finite-Width Neural Networks

Sidak Pal Singh, Aurelien Lucchi, Thomas Hofmann, Bernhard Schölkopf

Deep ReLU Networks Preserve Expected Length

Boris Hanin, Ryan Jeong, David Rolnick

A First-Occupancy Representation for Reinforcement Learning

Ted Moskovitz, Spencer R Wilson, Maneesh Sahani

TPU-GAN: Learning temporal coherence from dynamic point cloud sequences

Zijie Li, Tianqin Li, Amir Barati Farimani

Prototype memory and attention mechanisms for few shot image generation

Tianqin Li, Zijie Li, Andrew Luo, Harold Rockwell, Amir Barati Farimani

Learning to Generalize across Domains on Single Test Samples

Zehao Xiao, Xiantong Zhen, Ling Shao, Cees G. M. Snoek

Orchestrated Value Mapping for Reinforcement Learning

Mehdi Fatemi, Arash Tavakoli

Memory Augmented Optimizers for Deep Learning

Paul-Aymeric Martin McRae, Prasanna Parthasarathi, Mido Assran, Sarath Chandar

Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions

Arda Sahiner, Tolga Ergen, Batu Ozturkler, Burak Bartan, John M. Pauly

Visual Representation Learning Does Not Generalize Strongly Within the Same Domain

Lukas Schott, Julius von Kügelgen, Frederik Träuble, Peter Vincent Gehler, Chris Russell

Efficient Self-supervised Vision Transformers for Representation Learning

Chunyuan Li, Jianwei Yang, Pengchuan Zhang, Mei Gao, Bin Xiao

Low-Budget Active Learning via Wasserstein Distance: An Integer Programming Approach

Rafid Mahmood, Sanja Fidler, Marc T Law

Joint Shapley values: a measure of joint feature importance

Chris Harris, Richard Pymar, Colin Rowat

Provably Robust Adversarial Examples

Dimitar Iliev Dimitrov, Gagandeep Singh, Timon Gehr, Martin Vechev

Relational Learning with Variational Bayes

Kuang-Hung Liu

Augmented Sliced Wasserstein Distances

Xiongjie Chen, Yongxin Yang, Yunpeng Li

Toward Faithful Case-based Reasoning through Learning Prototypes in a Nearest Neighbor-friendly Space.

Seyed Omid Davoudi, Majid Komeili

Distributional Reinforcement Learning with Monotonic Splines

Yudong Luo, Guiliang Liu, Haonan Duan, Oliver Schulte, Pascal Poupart

Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representations

Sarath Sreedharan, Utkarsh Soni, Mudit Verma, Siddharth Srivastava, Subbarao Kambhampati

Network Augmentation for Tiny Deep Learning

Han Cai, Chuang Gan, Ji Lin, Song Han

Graphon based Clustering and Testing of Networks: Algorithms and Theory

Mahalakshmi Sabanayagam, Leena Chennuru Vankadara, Debarghya Ghoshdastidar

NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training

Chengyue Gong, Dilin Wang, Meng Li, Xinlei Chen, Zhicheng Yan

Learning Curves for SGD on Structured Features

Blake Bordelon, Cengiz Pehlevan

Towards Understanding the Robustness Against Evasion Attack on Categorical Data

Hongyan Bao, Yufei Han, Yujun Zhou, Yun Shen, Xiangliang Zhang

Tracking the risk of a deployed model and detecting harmful distribution shifts

Aleksandr Podkopaev, Aaditya Ramdas

The Effects of Invertibility on the Representational Complexity of Encoders in Variational Autoencoders

Divyansh Pareek, Andrej Risteski

Particle Stochastic Dual Coordinate Ascent: Exponential convergent algorithm for mean field neural network optimization

Kazusato Oko, Taiji Suzuki, Atsushi Nitanda, Denny Wu

Pix2seq: A Language Modeling Framework for Object Detection

Ting Chen, Saurabh Saxena, Lala Li, David J. Fleet, Geoffrey Hinton

NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs

Mikhail Galkin, Etienne Denis, Jiapeng Wu, William L. Hamilton

Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning

Natalie Dullerud, Karsten Roth, Kimia Hamidieh, Nicolas Papernot, Marzyeh Ghassemi

Triangle and Four Cycle Counting with Predictions in Graph Streams

Justin Y Chen, Talya Eden, Piotr Indyk, Honghao Lin, Shyam Narayanan

Fast AdvProp

Jieru Mei, Yucheng Han, Yutong Bai, Yixiao Zhang, Yingwei Li

Expressivity of Emergent Languages is a Trade-off between Contextual Complexity and Unpredictability

Shangmin Guo, Yi Ren, Kory Wallace Mathewson, Simon Kirby, Stefano V Albrecht

Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off

Rahul Rade, Seyed-Mohsen Moosavi-Dezfooli

Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient Descent

Oliver Bryniarski, Nabeel Hingun, Pedro Pachuca, Vincent Wang, Nicholas Carlini

Open-World Semi-Supervised Learning

Kaidi Cao, Maria Brbic, Jure Leskovec

Learning State Representations via Retracing in Reinforcement Learning

Changmin Yu, Dong Li, Jianye Hao, Jun Wang, Neil Burgess

Should I Run Offline Reinforcement Learning or Behavioral Cloning?

Aviral Kumar, Joey Hong, Anikait Singh, Sergey Levine

FedBABU: Toward Enhanced Representation for Federated Image Classification

Jaehoon Oh, SangMook Kim, Se-Young Yun

A Statistical Framework for Efficient Out of Distribution Detection in Deep Neural Networks

Matan Haroush, Tzviel Frostig, Ruth Heller, Daniel Soudry

Data Efficient Language-Supervised Zero-Shot Recognition with Optimal Transport Distillation

Bichen Wu, Ruizhe Cheng, Peizhao Zhang, Tianren Gao, Joseph E. Gonzalez

It Takes Two to Tango: Mixup for Deep Metric Learning

Shashanka Venkataramanan, Bill Psomas, Ewa Kijak, laurent amsaleg, Konstantinos Karantzalos

Modeling Label Space Interactions in Multi-label Classification using Box Embeddings

Dhruvesh Patel, Pavitra Dangati, Jay-Yoon Lee, Michael Boratko, Andrew McCallum

Geometry-Consistent Neural Shape Representation with Implicit Displacement Fields

Wang Yifan, Lukas Rahmann, Olga Sorkine-hornung

Multi-Agent MDP Homomorphic Networks

Elise van der Pol, Herke van Hoof, Frans A Oliehoek, Max Welling

Data-Driven Offline Optimization for Architecting Hardware Accelerators

Aviral Kumar, Amir Yazdanbakhsh, Milad Hashemi, Kevin Swersky, Sergey Levine

Sample Selection with Uncertainty of Losses for Learning with Noisy Labels

Xiaobo Xia, Tongliang Liu, Bo Han, Mingming Gong, Jun Yu

Efficient Token Mixing for Transformers via Adaptive Fourier Neural Operators

John Guibas, Morteza Mardani, Zongyi Li, Andrew Tao, Anima Anandkumar

Provable Adaptation across Multiway Domains via Representation Learning

Zhili Feng, Shaobo Han, Simon Shaolei Du

ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning

Vamsi Aribandi, Yi Tay, Tal Schuster, Jinfeng Rao, Huaixiu Steven Zheng

COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks

Fan Wu, Linyi Li, Huan Zhang, Bhavya Kailkhura, Krishnaram Kenthapadi

Chunked Autoregressive GAN for Conditional Waveform Synthesis

Max Morrison, Rithesh Kumar, Kundan Kumar, Prem Seetharaman, Aaron Courville