NeurIPS 2021

2,334 papers

Fast Tucker Rank Reduction for Non-Negative Tensors Using Mean-Field Approximation

Kazu Ghalamkari, Mahito Sugiyama

The Complexity of Bayesian Network Learning: Revisiting the Superstructure

Robert Ganian, Viktoriia Korchemna

Scalable Inference in SDEs by Direct Matching of the Fokker–Planck–Kolmogorov Equation

Arno Solin, Ella Tamir, Prakhar Verma

Local Explanation of Dialogue Response Generation

Yi-Lin Tuan, Connor Pryor, Wenhu Chen, Lise Getoor, William Yang Wang

Progressive Feature Interaction Search for Deep Sparse Network

Chen Gao, Yinfeng Li, Quanming Yao, Depeng Jin, Yong Li

Learning Space Partitions for Path Planning

Kevin Yang, Tianjun Zhang, Chris Cummins, Brandon Cui, Benoit Steiner

DRIVE: One-bit Distributed Mean Estimation

Shay Vargaftik, Ran Ben-Basat, Amit Portnoy, Gal Mendelson, Yaniv Ben-Itzhak

Learning to Select Exogenous Events for Marked Temporal Point Process

Ping Zhang, Rishabh Iyer, Ashish Tendulkar, Gaurav Aggarwal, Abir De

CentripetalText: An Efficient Text Instance Representation for Scene Text Detection

Tao Sheng, Jie Chen, Zhouhui Lian

Oracle Complexity in Nonsmooth Nonconvex Optimization

Guy Kornowski, Ohad Shamir

Predicting What You Already Know Helps: Provable Self-Supervised Learning

Jason Lee, Qi Lei, Nikunj Saunshi, JIACHENG ZHUO

VoiceMixer: Adversarial Voice Style Mixup

Sang-Hoon Lee, Hyunseung Chung, Seong-Whan Lee, Jihoon Kim, Ji-Hoon Kim

Meta-Learning Reliable Priors in the Function Space

Jonas Rothfuss, Dominique Heyn, jinfan Chen, Andreas Krause

Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods

Seohong Park, Jaekyeom Kim, Gunhee Kim

Habitat 2.0: Training Home Assistants to Rearrange their Habitat

Andrew Szot, Alexander Clegg, Eric Undersander, Erik Wijmans, Yili Zhao

AugMax: Adversarial Composition of Random Augmentations for Robust Training

Haotao Wang, Chaowei Xiao, Jean Kossaifi, Zhiding Yu, Anima Anandkumar

Revisiting Model Stitching to Compare Neural Representations

Yamini Bansal, Preetum Nakkiran, Boaz Barak

Approximating the Permanent with Deep Rejection Sampling

Juha Harviainen, Antti Röyskö, Mikko Koivisto

Multimodal Few-Shot Learning with Frozen Language Models

Maria Tsimpoukelli, Jacob L Menick, Serkan Cabi, S. M. Ali Eslami, Oriol Vinyals

Analytical Study of Momentum-Based Acceleration Methods in Paradigmatic High-Dimensional Non-Convex Problems

Stefano Sarao Mannelli, Pierfrancesco Urbani

Fast Training of Neural Lumigraph Representations using Meta Learning

Alexander Bergman, Petr Kellnhofer, Gordon Wetzstein

Non-local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation

Jogendra Nath Kundu, Siddharth Seth, Anirudh Jamkhandi, Pradyumna YM, Varun Jampani

ReAct: Out-of-distribution Detection With Rectified Activations

Yiyou Sun, Chuan Guo, Yixuan Li

Truncated Marginal Neural Ratio Estimation

Benjamin K Miller, Alex Cole, Patrick Forré, Gilles Louppe, Christoph Weniger

Backward-Compatible Prediction Updates: A Probabilistic Approach

Frederik Träuble, Julius von Kügelgen, Matthäus Kleindessner, Francesco Locatello, Bernhard Schölkopf

Hyperbolic Busemann Learning with Ideal Prototypes

Mina Ghadimi Atigh, Martin Keller-Ressel, Pascal Mettes

BAST: Bayesian Additive Regression Spanning Trees for Complex Constrained Domain

Zhao Tang Luo, Huiyan Sang, Bani Mallick

From Canonical Correlation Analysis to Self-supervised Graph Neural Networks

Hengrui Zhang, Qitian Wu, Junchi Yan, David P. Wipf, Philip S Yu

Counterfactual Explanations Can Be Manipulated

Dylan Slack, Anna Hilgard, Himabindu Lakkaraju, Sameer Singh

Finding Discriminative Filters for Specific Degradations in Blind Super-Resolution

Liangbin Xie, Xintao Wang, Chao Dong, Zhongang Qi, Ying Shan

UniDoc: Unified Pretraining Framework for Document Understanding

Jiuxiang Gu, Jason Kuen, Handong Zhao, Rajiv Jain, Nikolaos Barmpalios

Matrix factorisation and the interpretation of geodesic distance

Nick Whiteley, Annie Gray, Patrick Rubin-Delanchy

Learning One Representation to Optimize All Rewards

Ahmed Touati, Yann Ollivier

Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning

Christoph Dann, Teodor Vanislavov Marinov, Mehryar Mohri, Julian Zimmert