NeurIPS 2021

2,334 papers

Causal Abstractions of Neural Networks

Atticus Geiger, Hanson Lu, Thomas Icard, Christopher Potts

Permutation-Invariant Variational Autoencoder for Graph-Level Representation Learning

Robin Winter, Frank Noe, Djork-Arné Clevert

Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment

Yin Zhao, minquan wang, Longjun Cai

Combating Noise: Semi-supervised Learning by Region Uncertainty Quantification

Zhenyu Wang, Ya-Li Li, Ye Guo, Shengjin Wang

An Exponential Lower Bound for Linearly Realizable MDP with Constant Suboptimality Gap

Yuanhao Wang, Ruosong Wang, Sham Kakade

Compositional Transformers for Scene Generation

Dor Arad Hudson, Larry Zitnick

Model-Based Reinforcement Learning via Imagination with Derived Memory

Yao Mu, Yuzheng Zhuang, Bin Wang, Guangxiang Zhu, Wulong Liu

Private and Non-private Uniformity Testing for Ranking Data

Róbert Busa-Fekete, Dimitris Fotakis, Emmanouil Zampetakis

Causal Identification with Matrix Equations

Sanghack Lee, Elias Bareinboim

Locality defeats the curse of dimensionality in convolutional teacher-student scenarios

Alessandro Favero, Francesco Cagnetta, Matthieu Wyart

Deep Neural Networks as Point Estimates for Deep Gaussian Processes

Vincent Dutordoir, James Hensman, Mark van der Wilk, Carl Henrik Ek, Zoubin Ghahramani

Inverse Optimal Control Adapted to the Noise Characteristics of the Human Sensorimotor System

Matthias Schultheis, Dominik Straub, Constantin A Rothkopf

Differentiable Equilibrium Computation with Decision Diagrams for Stackelberg Models of Combinatorial Congestion Games

Shinsaku Sakaue, Kengo Nakamura

Learning Graph Models for Retrosynthesis Prediction

Vignesh Ram Somnath, Charlotte Bunne, Connor Coley, Andreas Krause, Regina Barzilay

Reliable Post hoc Explanations: Modeling Uncertainty in Explainability

Dylan Slack, Anna Hilgard, Sameer Singh, Himabindu Lakkaraju

Data-Efficient Instance Generation from Instance Discrimination

Ceyuan Yang, Yujun Shen, Yinghao Xu, Bolei Zhou

Evaluating State-of-the-Art Classification Models Against Bayes Optimality

Ryan Theisen, Huan Wang, Lav R. Varshney, Caiming Xiong, Richard Socher

Twins: Revisiting the Design of Spatial Attention in Vision Transformers

Xiangxiang Chu, Zhi Tian, Yuqing Wang, Bo Zhang, Haibing Ren

Integrating Tree Path in Transformer for Code Representation

Han Peng, Ge Li, Wenhan Wang, YunFei Zhao, Zhi Jin

TacticZero: Learning to Prove Theorems from Scratch with Deep Reinforcement Learning

Minchao Wu, Michael Norrish, Christian Walder, Amir Dezfouli

Differentially Private Stochastic Optimization: New Results in Convex and Non-Convex Settings

Raef Bassily, Cristóbal Guzmán, Michael Menart

Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes

Sanghyun Hong, Michael-Andrei Panaitescu-Liess, Yigitcan Kaya, Tudor Dumitras

Realistic evaluation of transductive few-shot learning

Olivier Veilleux, Malik Boudiaf, Pablo Piantanida, Ismail Ben Ayed

Hierarchical Clustering: $O(1)$-Approximation for Well-Clustered Graphs

Bogdan-Adrian Manghiuc, He Sun

A Highly-Efficient Group Elastic Net Algorithm with an Application to Function-On-Scalar Regression

Tobia Boschi, Matthew Reimherr, Francesca Chiaromonte

Efficient Statistical Assessment of Neural Network Corruption Robustness

Karim TIT, Teddy Furon, Mathias ROUSSET

Adversarial Examples in Multi-Layer Random ReLU Networks

Peter L. Bartlett, Sébastien Bubeck, Yeshwanth Cherapanamjeri

Dynamics of Stochastic Momentum Methods on Large-scale, Quadratic Models

Courtney Paquette, Elliot Paquette

An Image is Worth More Than a Thousand Words: Towards Disentanglement in The Wild

Aviv Gabbay, Niv Cohen, Yedid Hoshen

Pay Attention to MLPs

Hanxiao Liu, Zihang Dai, David So, Quoc V Le

High Probability Complexity Bounds for Line Search Based on Stochastic Oracles

Billy Jin, Katya Scheinberg, Miaolan Xie

Analyzing the Confidentiality of Undistillable Teachers in Knowledge Distillation

Souvik Kundu, Qirui Sun, Yao Fu, Massoud Pedram, Peter Beerel

When Expressivity Meets Trainability: Fewer than n Neurons Can Work

Jiawei Zhang, Yushun Zhang, Mingyi Hong, Ruoyu Sun, Zhi-Quan Luo

ROI Maximization in Stochastic Online Decision-Making

Nicolò Cesa-bianchi, Tom Cesari, Yishay Mansour, Vianney Perchet

Differentiable Learning Under Triage

Nastaran Okati, Abir De, Manuel Rodriguez

Differentially Private Federated Bayesian Optimization with Distributed Exploration

Zhongxiang Dai, Bryan Kian Hsiang Low, Patrick Jaillet

Attention over Learned Object Embeddings Enables Complex Visual Reasoning

David Ding, Felix Hill, Adam Santoro, Malcolm Reynolds, Matt Botvinick

Denoising Normalizing Flow

Christian Horvat, Jean-pascal Pfister

General Nonlinearities in SO(2)-Equivariant CNNs

Daniel Franzen, Michael Wand

SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients

Feihu Huang, Junyi Li, Heng Huang

Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning

Muhan Zhang, Pan Li, Yinglong Xia, Kai Wang, Long Jin

Generalizable Multi-linear Attention Network

Tao Jin, Zhou Zhao

Consistent Non-Parametric Methods for Maximizing Robustness

Robi Bhattacharjee, Kamalika Chaudhuri

Asynchronous Stochastic Optimization Robust to Arbitrary Delays

Alon Cohen, Amit Daniely, Yoel Drori, Tomer Koren, Mariano Schain

CATs: Cost Aggregation Transformers for Visual Correspondence

Seokju Cho, Sunghwan Hong, Sangryul Jeon, Yunsung Lee, Kwanghoon Sohn

What can linearized neural networks actually say about generalization?

Guillermo Ortiz-Jimenez, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard

Scalable Neural Data Server: A Data Recommender for Transfer Learning

Tianshi Cao, Sasha (Alexandre) Doubov, David Acuna, Sanja Fidler

Going Beyond Linear RL: Sample Efficient Neural Function Approximation

Baihe Huang, Kaixuan Huang, Sham Kakade, Jason Lee, Qi Lei

Refining Language Models with Compositional Explanations

Huihan Yao, Ying Chen, Qinyuan Ye, Xisen Jin, Xiang Ren

On Riemannian Optimization over Positive Definite Matrices with the Bures-Wasserstein Geometry

Andi Han, Bamdev Mishra, Pratik Kumar Jawanpuria, Junbin Gao

Gone Fishing: Neural Active Learning with Fisher Embeddings

Jordan Ash, Surbhi Goel, Akshay Krishnamurthy, Sham Kakade

On Empirical Risk Minimization with Dependent and Heavy-Tailed Data

Abhishek Roy, Krishnakumar Balasubramanian, Murat A Erdogdu

Multiple Descent: Design Your Own Generalization Curve

Lin Chen, Yifei Min, Mikhail Belkin, Amin Karbasi

Cooperative Stochastic Bandits with Asynchronous Agents and Constrained Feedback

Lin Yang, Yu-Zhen Janice Chen, Stephen Pasteris, Mohammad Hajiesmaili, Don Towsley

How Fine-Tuning Allows for Effective Meta-Learning

Kurtland Chua, Qi Lei, Jason Lee

Interpreting Representation Quality of DNNs for 3D Point Cloud Processing

Wen Shen, Qihan Ren, Dongrui Liu, Quanshi Zhang

Equilibrium Refinement for the Age of Machines: The One-Sided Quasi-Perfect Equilibrium

Gabriele Farina, Tuomas Sandholm

A Biased Graph Neural Network Sampler with Near-Optimal Regret

Qingru Zhang, David P. Wipf, Quan Gan, Le Song

SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimization

Amir Hertz, Or Perel, Raja Giryes, Olga Sorkine-hornung, Daniel Cohen-or

A Closer Look at the Worst-case Behavior of Multi-armed Bandit Algorithms

Anand Kalvit, Assaf J. Zeevi

Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Making by Reinforcement Learning

Kai Wang, Sanket Shah, Haipeng Chen, Andrew Perrault, Finale Doshi-velez

Diffusion Models Beat GANs on Image Synthesis

Prafulla Dhariwal, Alexander Nichol

The Unbalanced Gromov Wasserstein Distance: Conic Formulation and Relaxation

Thibault Sejourne, Francois-Xavier Vialard, Gabriel Peyré

Inverse Problems Leveraging Pre-trained Contrastive Representations

Sriram Ravula, Georgios Smyrnis, Matt Jordan, Alexandros G Dimakis

Raw Nav-merge Seismic Data to Subsurface Properties with MLP based Multi-Modal Information Unscrambler

Aditya Desai, Zhaozhuo Xu, Menal Gupta, Anu Chandran, Antoine Vial-Aussavy

Relative stability toward diffeomorphisms indicates performance in deep nets

Leonardo Petrini, Alessandro Favero, Mario Geiger, Matthieu Wyart

Searching the Search Space of Vision Transformer

Minghao Chen, Kan Wu, Bolin Ni, Houwen Peng, Bei Liu

Ranking Policy Decisions

Hadrien Pouget, Hana Chockler, Youcheng Sun, Daniel Kroening

Synthetic Design: An Optimization Approach to Experimental Design with Synthetic Controls

Nick Doudchenko, Khashayar Khosravi, Jean Pouget-Abadie, Sebastien Lahaie, Miles Lubin

Multi-Facet Clustering Variational Autoencoders

Fabian Falck, Haoting Zhang, Matthew Willetts, George Nicholson, Christopher Yau

Towards Gradient-based Bilevel Optimization with Non-convex Followers and Beyond

Risheng Liu, Yaohua Liu, Shangzhi Zeng, Jin Zhang

L2ight: Enabling On-Chip Learning for Optical Neural Networks via Efficient in-situ Subspace Optimization

Jiaqi Gu, Hanqing Zhu, Chenghao Feng, Zixuan Jiang, Ray Chen

Machine Learning for Variance Reduction in Online Experiments

Yongyi Guo, Dominic Coey, Mikael Konutgan, Wenting Li, Chris Schoener

Adversarial Intrinsic Motivation for Reinforcement Learning

Ishan Durugkar, Mauricio Tec, Scott Niekum, Peter Stone

Stability & Generalisation of Gradient Descent for Shallow Neural Networks without the Neural Tangent Kernel

Dominic Richards, Ilja Kuzborskij

Two-sided fairness in rankings via Lorenz dominance

Virginie Do, Sam Corbett-Davies, Jamal Atif, Nicolas Usunier

Scaling Vision with Sparse Mixture of Experts

Carlos Riquelme, Joan Puigcerver, Basil Mustafa, Maxim Neumann, Rodolphe Jenatton

HyperSPNs: Compact and Expressive Probabilistic Circuits

Andy Shih, Dorsa Sadigh, Stefano Ermon

AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks

Alexandra Peste, Eugenia Iofinova, Adrian Vladu, Dan Alistarh

Escape saddle points by a simple gradient-descent based algorithm

Chenyi Zhang, Tongyang Li

Mixture Proportion Estimation and PU Learning:A Modern Approach

Saurabh Garg, Yifan Wu, Alexander J Smola, Sivaraman Balakrishnan, Zachary Lipton

Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems

Suhas Kowshik, Dheeraj Nagaraj, Prateek Jain, Praneeth Netrapalli

On the interplay between data structure and loss function in classification problems

Stéphane d'Ascoli, Marylou Gabrie, Levent Sagun, Giulio Biroli

Ensembling Graph Predictions for AMR Parsing

Thanh Lam Hoang, Gabriele Picco, Yufang Hou, Young-Suk Lee, Lam Nguyen

Exploring Social Posterior Collapse in Variational Autoencoder for Interaction Modeling

Chen Tang, Wei Zhan, Masayoshi Tomizuka

Active clustering for labeling training data

Quentin Lutz, Elie de Panafieu, Maya Stein, Alex Scott

Parameter-free HE-friendly Logistic Regression

Junyoung Byun, Woojin Lee, Jaewook Lee

Multilingual Pre-training with Universal Dependency Learning

Kailai Sun, Zuchao Li, Hai Zhao

Offline Model-based Adaptable Policy Learning

Xiong-Hui Chen, Yang Yu, Qingyang Li, Fan-Ming Luo, Zhiwei Qin

Implicit SVD for Graph Representation Learning

Sami Abu-El-Haija, Hesham Mostafa, Marcel Nassar, Valentino Crespi, Greg Ver Steeg

Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures

Yuan Cao, Quanquan Gu, Mikhail Belkin

Personalized Federated Learning With Gaussian Processes

Idan Achituve, Aviv Shamsian, Aviv Navon, Gal Chechik, Ethan Fetaya

Locally Valid and Discriminative Prediction Intervals for Deep Learning Models

Zhen Lin, Shubhendu Trivedi, Jimeng Sun

Diversity Matters When Learning From Ensembles

Giung Nam, Jongmin Yoon, Yoonho Lee, Juho Lee

Learning Debiased and Disentangled Representations for Semantic Segmentation

Sanghyeok Chu, Dongwan Kim, Bohyung Han

On the Suboptimality of Thompson Sampling in High Dimensions

Raymond Zhang, Richard Combes

Low-dimensional Structure in the Space of Language Representations is Reflected in Brain Responses

Richard Antonello, Javier S Turek, Vy Vo, Alexander Huth

Learning Signal-Agnostic Manifolds of Neural Fields

Yilun Du, Katie Collins, Josh Tenenbaum, Vincent Sitzmann

Uniform Concentration Bounds toward a Unified Framework for Robust Clustering

Debolina Paul, Saptarshi Chakraborty, Swagatam Das, Jason Xu

Measuring Generalization with Optimal Transport

Ching-Yao Chuang, Youssef Mroueh, Kristjan Greenewald, Antonio Torralba, Stefanie Jegelka