Accept paper list: link

anomaly detection

• Energy-based Out-of-distribution Detection

  Weitang Liu (UC San Diego) · Xiaoyun Wang (University of California, Davis) · John Owens (University of California, Davis) · Sharon Yixuan Li (Stanford University)

• Provable Worst Case Guarantees for the Detection of Out-of-distribution Data

  Julian Bitterwolf (University of Tübingen) · Alexander Meinke (University of Tübingen) · Matthias Hein (University of Tübingen)

• Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder

  Zhisheng Xiao (The University of Chicago) · Qing Yan (University of Chicago) · Yali Amit (University of Chicago)

• Why Normalizing Flows Fail to Detect Out-of-Distribution Data

  Polina Kirichenko (New York University) · Pavel Izmailov (New York University) · Andrew Gordon Wilson (New York University)

• 【看看5】 Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples

  Jay Nandy (National University of Singapore) · Wynne Hsu (National University of Singapore) · Mong Li Lee (National University of Singapore)

• On the Value of Out-of-Distribution Testing: An Example of Goodhart’s Law

  Damien Teney (University of Adelaide) · Ehsan Abbasnejad (University of Adelaide) · Kushal Kafle (Adobe Research) · Robik Shrestha (Rochester Institute of Technology) · Christopher Kanan (PAIGE.AI / RIT / CornellTech) · Anton van den Hengel (University of Adelaide)

• Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Features

  Robin T Schirrmeister (University Medical Center Freiburg) · Yuxuan Zhou (Stuttgart University) · Tonio Ball (Albert-Ludwigs-University) · Dan Zhang (Bosch Center for Artificial Intelligence)

• 【看看1】 Timeseries Anomaly Detection using Temporal Hierarchical One-Class Network

  Lifeng Shen (The Hong Kong University of Science and Technology) · Zhuocong Li (Tencent) · James Kwok (Hong Kong University of Science and Technology)

• CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances

  Jihoon Tack (KAIST) · Sangwoo Mo (KAIST) · Jongheon Jeong (KAIST) · Jinwoo Shin (KAIST)

• 【看看4】 One Ring to Rule Them All: Certifiably Robust Geometric Perception with Outliers

  Heng Yang · Luca Carlone

• 【看看3】 Outlier Robust Mean Estimation with Subgaussian Rates via Stability

  Ilias Diakonikolas · Daniel M. Kane · Ankit Pensia

• 【看看2】 Further Analysis of Outlier Detection with Deep Generative Models

  Ziyu Wang · Bin Dai · David P Wipf · Jun Zhu

Time series

• Probabilistic Time Series Forecasting with Shape and Temporal Diversity

  Vincent LE GUEN (CNAM, Paris, France) · Nicolas THOME (Cnam (Conservatoire national des arts et métiers))

• 【看看ts-5】 Deep reconstruction of strange attractors from time series

  William Gilpin (Harvard University)

• Deep Energy-based Modeling of Discrete-Time Physics

  Takashi Matsubara (Osaka University) · Ai Ishikawa (Kobe University) · Takaharu Yaguchi (Kobe University)

• 【看看ts-3】 Neural Controlled Differential Equations for Irregular Time Series

  Patrick Kidger (University of Oxford) · James Morrill (University of Oxford) · James Foster (University of Oxford) · Terry Lyons (University of Oxford)

• 【看看ts-4】 Adversarial Sparse Transformer for Time Series Forecasting

  Sifan Wu (Tsinghua University) · Xi Xiao (Tsinghua University) · Qianggang Ding (Tsinghua University) · Peilin Zhao (Tencent AI Lab) · Ying Wei (Tencent AI Lab) · Junzhou Huang (University of Texas at Arlington / Tencent AI Lab)

• 【看看ts-2】 Learning Long-Term Dependencies in Irregularly-Sampled Time Series

  Mathias Lechner (IST Austria) · Ramin Hasani (MIT)

• 【看看ts-1】 Benchmarking Deep Learning Interpretability in Time Series Predictions

  Aya Abdelsalam Ismail (University of Maryland) · Mohamed Gunady (University of Maryland) · Hector Corrada Bravo (University of Maryland) · Soheil Feizi (University of Maryland)

• High-recall causal discovery for autocorrelated time series with latent confounders

  Andreas Gerhardus (German Aerospace Center (DLR)) · Jakob Runge (Institute of Data Science, German Aerospace Center (DLR))

• Deep Rao-Blackwellised Particle Filters for Time Series Forecasting

  Richard Kurle (Volkswagen Group) · Syama Sundar Rangapuram (Amazon Research) · Emmanuel de Bézenac (Sorbonne Université) · Stephan Günnemann (Technical University of Munich) · Jan Gasthaus (Amazon.com)

• Normalizing Kalman Filters for Multivariate Time Series Analysis

  Emmanuel de Bézenac (Sorbonne Université) · Syama Sundar Rangapuram (Amazon Research) · Konstantinos Benidis (Amazon Research) · Michael Bohlke-Schneider (Amazon) · Lorenzo Stella (Amazon Research) · Hilaf Hasson (Amazon Research) · Richard Kurle (Volkswagen Group) · Tim Januschowski (Amazon Research) · Patrick Gallinari (Sorbonne University & Criteo AI Lab, Paris)

• User-Dependent Neural Sequence Models for Continuous-Time Event Data

  Alex Boyd (UC Irvine) · Robert Bamler (University of California at Irvine) · Stephan Mandt (University of California, Irivine) · Padhraic Smyth (University of California, Irvine)

About distribution

• Distribution-free binary classification: prediction sets, confidence intervals and calibration

  Chirag Gupta (Carnegie Mellon University) · Aleksandr Podkopaev (Carnegie Mellon University) · Aaditya Ramdas (CMU)

• Deep Diffusion-Invariant Wasserstein Distributional Classification

  Sung Woo Park+ (Chung-Ang University) · Dong Wook Shu (Chung-Ang Univ., Korea) · Junseok Kwon (Chung-Ang Univ., Korea)

• OOD-MAML: Meta-Learning for Few-Shot Out-of-Distribution Detection and Classification

  Taewon Jeong (KAIST) · Heeyoung Kim (KAIST)

• Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Features

  Robin T Schirrmeister (University Medical Center Freiburg) · Yuxuan Zhou (Stuttgart University) · Tonio Ball (Albert-Ludwigs-University) · Dan Zhang (Bosch Center for Artificial Intelligence)

• Measuring Robustness to Natural Distribution Shifts in Image Classification

  Rohan Taori (University of California, Berkeley) · Achal Dave (Carnegie Mellon University) · Vaishaal Shankar (UC Berkeley) · Nicholas Carlini (Google) · Benjamin Recht (UC Berkeley) · Ludwig Schmidt (UC Berkeley)

• Fast Epigraphical Projection-based Incremental Algorithms for Wasserstein Distributionally Robust Support Vector Machine

  Jiajin Li (The Chinese University of Hong Kong) · Caihua Chen (Nanjing University) · Anthony Man-Cho So (CUHK)

• Adversarial Distributional Training for Robust Deep Learning

  Yinpeng Dong (Tsinghua University) · Zhijie Deng (Tsinghua University) · Tianyu Pang (Tsinghua University) · Hang Su (Tsinghua Univiersity) · Jun Zhu (Tsinghua University)

• Mix and Match: An Optimistic Tree-Search Approach for Learning Models from Mixture Distributions

  Matthew Faw (University of Texas at Austin) · Rajat Sen (Amazon) · Karthikeyan Shanmugam (IBM Research, NY) · Constantine Caramanis (UT Austin) · Sanjay Shakkottai (University of Texas at Austin)

• Distributionally Robust Parametric Maximum Likelihood Estimation

  Viet Anh Nguyen (Stanford University) · Xuhui Zhang (Stanford University) · Jose Blanchet (Stanford University) · Angelos Georghiou (University of Cyprus)

• Distributionally Robust Local Non-parametric Conditional Estimation

  Viet Anh Nguyen (Stanford University) · Fan Zhang (Stanford University) · Jose Blanchet (Stanford University) · Erick Delage (HEC Montréal) · Yinyu Ye (Standord)

• Large-Scale Methods for Distributionally Robust Optimization

  Daniel Levy (Stanford University) · Yair Carmon (Stanford University) · John Duchi (Stanford) · Aaron Sidford (Stanford)

• Efficient Distance Approximation for Structured High-Dimensional Distributions via Learning

  Arnab Bhattacharyya (National University of Singapore) · Sutanu Gayen (National University of SIngapore) · Kuldeep S Meel (National University of Singapore) · N. V. Vinodchandran (University of Nebraska)

• Analytical Probability Distributions and EM-Learning for Deep Generative Networks

  Randall Balestriero (Rice University) · Sebastien PARIS (University of Toulon) · Richard Baraniuk (Rice University)

• 【看看dis-1】 Learning Structured Distributions From Untrusted Batches: Faster and Simpler

  Sitan Chen (MIT) · Jerry Li (Microsoft) · Ankur Moitra (MIT)

• Linear-Sample Learning of Low-Rank Distributions

  Ayush Jain (UC San Diego) · Alon Orlitsky (University of California, San Diego)

• Profile Entropy: A Fundamental Measure for the Learnability and Compressibility of Distributions

  Yi Hao (University of California, San Diego) · Alon Orlitsky (University of California, San Diego)

• 【看看dis-2】 SURF: A Simple, Universal, Robust, Fast Distribution Learning Algorithm

  Yi Hao (University of California, San Diego) · Ayush Jain (UC San Diego) · Alon Orlitsky (University of California, San Diego) · Vaishakh Ravindrakumar (UC San Diego)

• Learning discrete distributions with infinite support

  Doron Cohen (Ben-Gurion University of the Negev) · Aryeh Kontorovich (Ben Gurion University) · Geoffrey Wolfer (Ben-Gurion University of the Negev)

• Optimal Private Median Estimation under Minimal Distributional Assumptions

  Christos Tzamos (UW-Madison) · Emmanouil-Vasileios Vlatakis-Gkaragkounis (Columbia University) · Ilias Zadik (NYU)

missing value & irregularly sampled time series

• Estimation and Imputation in Probabilistic Principal Component Analysis with Missing Not At Random Data

  Aude Sportisse (Sorbonne University, Ecole Polytechnique) · Claire Boyer (LPSM, Sorbonne Université) · Julie Josses (CMAP / CNRS)

• 【看看missing-2】 Learning Disentangled Representations of Videos with Missing Data

  Armand Comas (Northeastern University) · Chi Zhang (Northeastern University) · Zlatan Feric (Northeastern University) · Octavia Camps (Northeastern University) · Rose Yu (University of California, San Diego)

• 【看看missing-3】 Debiasing Averaged Stochastic Gradient Descent to handle missing values

  Aude Sportisse (Sorbonne University, Ecole Polytechnique) · Claire Boyer (LPSM, Sorbonne Université) · Aymeric Dieuleveut (Ecole Polytechnique, IPParis) · Julie Josses (CMAP / CNRS)

• Handling Missing Data with Graph Representation Learning

  Jiaxuan You (Stanford University) · Xiaobai Ma (Stanford University) · Yi Ding (Stanford University) · Mykel J Kochenderfer (Stanford University) · Jure Leskovec (Stanford University and Pinterest)

• A Functional EM Algorithm for Panel Count Data with Missing Counts

  Alexander Moreno (Georgia Institute of Technology) · Zhenke Wu (University of Michigan) · Jamie Roslyn Yap (University of Michigan) · Cho Lam (University of Utah) · David Wetter (University of Utah) · Inbal Nahum-Shani (University of Michigan) · Walter Dempsey (University of Michigan) · James M Rehg (Georgia Tech)

• NeuMiss networks: differentiable programming for supervised learning with missing values.

  Marine Le Morvan (INRIA) · Julie Josses (CMAP / CNRS) · Thomas Moreau (Inria) · Erwan Scornet (Ecole Polytechnique) · Gael Varoquaux (Parietal Team, INRIA)

• 【看看missing-1】 Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations

  Zijie Huang (University of California, Los Angeles) · Yizhou Sun (UCLA) · Wei Wang (UCLA)

Recurrent Neural Network

• Convolutional Tensor-Train LSTM for Spatio-Temporal Learning

  Jiahao Su (University of Maryland) · Wonmin Byeon (NVIDIA Research) · Jean Kossaifi (NVIDIA) · Furong Huang (University of Maryland) · Jan Kautz (NVIDIA) · Anima Anandkumar (NVIDIA / Caltech)

• RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference

  Oindrila Saha (Microsoft Research) · Aditya Kusupati (University of Washington) · Harsha Vardhan Simhadri (Microsoft Research) · Manik Varma (Microsoft Research India) · Prateek Jain (Microsoft Research)

• 【看看other-3】 The interplay between randomness and structure during learning in RNNs

  Friedrich Schuessler (Technion) · Francesca Mastrogiuseppe (UCL) · Alexis Dubreuil (ENS) · Srdjan Ostojic (Ecole Normale Superieure) · Omri Barak (Technion - Israeli institute of technology)

• 【看看other-4】 HiPPO: Recurrent Memory with Optimal Polynomial Projections

  Albert Gu (Stanford) · Tri Dao (Stanford University) · Stefano Ermon (Stanford) · Atri Rudra (University at Buffalo, SUNY) · Christopher Ré (Stanford)

• RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning

  Riccardo Del Chiaro (University of Florence) · Bartłomiej Twardowski (Computer Vision Center, UAB) · Andrew D Bagdanov (University of Florence) · Joost van de Weijer (Computer Vision Center Barcelona)

• MomentumRNN: Integrating Momentum into Recurrent Neural Networks

  Tan Nguyen (Rice University/UCLA) · Richard Baraniuk (Rice University) · Andrea Bertozzi (UCLA) · Stanley Osher (UCLA) · Bao Wang (UCLA)

• Recurrent Random Networks as Optimized Kernel Machines

  Sandra Nestler (Juelich Research Centre) · Christian Keup (Juelich Research Centre) · David Dahmen (Jülich Research Centre) · Matthieu Gilson (Juelich Forschungszentrum) · Holger Rauhut (RWTH Aachen University) · Moritz Helias (Juelich Research Centre)

• Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting

  LEI BAI (UNSW, Sydney) · Lina Yao (University of New South Wales) · Can Li (University of New South Wales) · Xianzhi Wang (University of Technology Sydney) · Can Wang (Griffith University)

• Using noise to probe recurrent neural network structure and prune synapses

  Eli Moore (University of California, Davis) · Rishidev Chaudhuri (University of California, Davis)

• Regularizing Towards Permutation Invariance In Recurrent Models

  Edo Cohen-Karlik (Tel Aviv University) · Avichai Ben David (Tel Aviv University) · Amir Globerson (Tel Aviv University, Google)

• STLnet: Signal Temporal Logic Enforced Multivariate Recurrent Neural Networks

  Meiyi Ma (University of Virginia) · Ji Gao (University of Virginia) · Lu Feng (University of Virginia) · John A Stankovic (University of Virginia)

• Organizing recurrent network dynamics by task-computation to enable continual learning

  Lea Duncker (Gatsby Unit, UCL) · Laura N Driscoll (Stanford) · Krishna V Shenoy (Stanford University) · Maneesh Sahani (Gatsby Unit, UCL) · David Sussillo (Stanford University)

• Recurrent Quantum Neural Networks

  Johannes Bausch (University of Cambridge)

• Reverse-engineering recurrent neural network solutions to a hierarchical inference task for mice

  Rylan Schaeffer (Harvard University) · Mikail C Khona (MIT) · Leenoy Meshulam (Massachusetts Institute of Technology MIT) · Brain Laboratory International (International Brain Laboratory) · Ila Fiete (Massachusetts Institute of Technology)

• Recurrent Switching Dynamical Systems Models for Multiple Interacting Neural Populations

  Joshua Glaser (Columbia) · Matthew Whiteway (Columbia University) · John Cunningham (University of Columbia) · Liam Paninski (Columbia University) · Scott Linderman (Stanford University)

sequence

• 【看看other-1】 Big Bird: Bert for Longer Sequences

  Manzil Zaheer (Google Research) · Guru Guruganesh (Google Research) · Kumar Avinava Dubey (Carnegie Mellon University) · Joshua Ainslie (Google) · Chris Alberti (Google) · Santiago Ontanon (Google LLC) · Philip Pham (Google) · Anirudh Ravula (Google) · Qifan Wang (Google Research) · Li Yang (Google) · Amr Ahmed (Google Research)

interpretable

• Explaining Naive Bayes and Other Linear Classifiers with Polynomial Time and Delay

  Joao Marques-Silva (ANITI, Federal University of Toulouse Midi-Pyrénées) · Thomas Gerspacher (ANITI) · Martin Cooper (University of Toulouse 3) · Alexey Ignatiev (Monash University) · Nina Narodytska (VMmare Research)

• 【看看interpre-3】 Interpretable Sequence Learning for Covid-19 Forecasting

  Sercan Arik (Google) · Chun-Liang Li (Google) · Martin Nikoltchev (Google) · Rajarishi Sinha (Google) · Arkady Epshteyn (Google) · Jinsung Yoon (Google) · Long Le (Google) · Vikas Menon (Google) · Shashank Singh (Google) · Yash Sonthalia (Google) · Hootan Nakhost (Google) · Leyou Zhang (Google) · Elli Kanal (Google) · Tomas Pfister (Google)

• ICAM: Interpretable Classification via Disentangled Representations and Feature Attribution Mapping

  Cher Bass (King’s College London) · Mariana da Silva (King’s College London) · Carole Sudre (King’s College London) · Petru-Daniel Tudosiu (King’s College London) · Stephen Smith (FMRIB Centre - University of Oxford) · Emma Robinson (King’s College)

• How does this interaction affect me? Interpretable attribution for feature interactions

  Michael Tsang (University of Southern California) · Sirisha Rambhatla (University of Southern California) · Yan Liu (University of Southern California)

• 【看看interpre-1】 Learning outside the Black-Box: The pursuit of interpretable models

  Jonathan Crabbe (University of Cambridge) · Yao Zhang (University of Cambridge) · William Zame (UCLA) · Mihaela van der Schaar (University of Cambridge)

• GANSpace: Discovering Interpretable GAN Controls

  Erik Härkönen (Aalto University) · Aaron Hertzmann (Adobe) · Jaakko Lehtinen (Aalto University & NVIDIA) · Sylvain Paris (Adobe)

• Interpretable multi-timescale models for predicting fMRI responses to continuous natural speech

  Shailee Jain (The University of Texas at Austin) · Vy Vo (Intel Corporation) · Shivangi Mahto (The University of Texas at Austin) · Amanda LeBel (The University of Texas at Austin) · Javier Turek (Intel Labs) · Alexander Huth (The University of Texas at Austin)

• Learning identifiable and interpretable latent models of high-dimensional neural activity using pi-VAE

  Ding Zhou (Columbia University) · Xue-Xin Wei (University of Pennsylvania)

• Towards Interpretable Natural Language Understanding with Explanations as Latent Variables

  Wangchunshu Zhou (Beihang University) · Jinyi Hu (Tsinghua University) · Hanlin Zhang (South China University of Technology) · Xiaodan Liang (Sun Yat-sen University) · Maosong Sun (Tsinghua University) · Chenyan Xiong (Microsoft Research AI) · Jian Tang (Mila)

• Interpretable and Personalized Apprenticeship Scheduling: Learning Interpretable Scheduling Policies from Heterogeneous User Demonstrations

  Rohan Paleja (Georgia Institute of Technology) · Andrew Silva (Georgia Institute of Technology) · Letian Chen (Georgia Institute of Technology) · Matthew Gombolay (Georgia Institute of Technology)

• Incorporating Interpretable Output Constraints in Bayesian Neural Networks

  Wanqian Yang (Harvard University) · Lars Lorch (Harvard) · Moritz Graule (Harvard University) · Himabindu Lakkaraju (Harvard) · Finale Doshi-Velez (Harvard)

• Implicit Regularization in Deep Learning May Not Be Explainable by Norms

  Noam Razin (Tel Aviv University) · Nadav Cohen (Tel Aviv University)

• Parameterized Explainer for Graph Neural Network

  Dongsheng Luo (The Pennsylvania State University) · Wei Cheng (NEC Labs America) · Dongkuan Xu (The Pennsylvania State University) · Wenchao Yu (UCLA) · Bo Zong (NEC Labs) · Haifeng Chen (NEC Labs America) · Xiang Zhang (The Pennsylvania State University)

• PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks

  Minh N Vu (University of Florida) · My T. Thai (University of Florida)

• Can Implicit Bias Explain Generalization? Stochastic Convex Optimization as a Case Study

  Assaf Dauber (Tel-Aviv University) · Meir Feder (Tel-Aviv University) · Tomer Koren (Tel Aviv University & Google) · Roi Livni (Tel Aviv University)

• Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability

  Christopher Frye (Faculty) · Colin Rowat (University of Birmingham) · Ilya Feige (Faculty)

• 【看看interpre-2】 How Can I Explain This to You? An Empirical Study of Deep Neural Network Explanation Methods

  Jeya Vikranth Jeyakumar (University of California, Los Angeles) · Joseph Noor (University of California, Los Angeles) · Yu-Hsi Cheng (UCLA) · Luis Garcia (University of California, Los Angeles) · Mani Srivastava (UCLA)

• Explainable Voting

  Dominik Peters (Carnegie Mellon University) · Ariel Procaccia (Harvard University) · Alexandros Psomas (Purdue University) · Zixin Zhou (Peking University)

• What Did You Think Would Happen? Explaining Agent Behaviour through Intended Outcomes

  Herman Ho-Man Yau (University of Surrey) · Chris Russell (The Alan Turing Institute/ The University of Surrey) · Simon Hadfield (University of Surrey)

• Margins are Insufficient for Explaining Gradient Boosting

  Allan Grønlund (Aarhus University, MADALGO) · Lior Kamma (Aarhus University) · Kasper Green Larsen (Aarhus University)

• Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models

  Tom Heskes (Radboud University Nijmegen) · Evi Sijben (Radboud University) · Ioan Gabriel Bucur (Radboud University Nijmegen) · Tom Claassen (Radboud University Nijmegen)

Autoencoder

• Implicit Rank-Minimizing Autoencoder

  Li Jing (Facebook AI Research) · Jure Zbontar (Facebook) · yann lecun (Facebook)

• Swapping Autoencoder for Deep Image Manipulation

  Taesung Park (UC Berkeley) · Jun-Yan Zhu (Adobe, CMU) · Oliver Wang (Adobe Research) · Jingwan Lu (Adobe Research) · Eli Shechtman (Adobe Research, US) · Alexei Efros (UC Berkeley) · Richard Zhang (Adobe)

• 【看看other-5】 Hierarchical Quantized Autoencoders

  Will Williams (Speechmatics) · Sam Ringer (Speechmatics) · Tom Ash (Speechmatics) · David MacLeod (Speechmatics) · Jamie Dougherty (Speechmatics) · John Hughes (Speechmatics)

• Regularized linear autoencoders recover the principal components, eventually

  Xuchan Bao (University of Toronto) · James Lucas (University of Toronto) · Sushant Sachdeva (University of Toronto) · Roger Grosse (University of Toronto)

• Dirichlet Graph Variational Autoencoder

  Jia Li (The Chinese University of Hong Kong) · Jianwei Yu (CUHK) · Jiajin Li (The Chinese University of Hong Kong) · Honglei Zhang (Georgia Institute of Technology) · Kangfei Zhao (The Chinese University of Hong Kong) · Yu Rong (Tencent AI Lab) · Hong Cheng (The Chinese University of Hong Kong) · Junzhou Huang (University of Texas at Arlington / Tencent AI Lab)

• NVAE: A Deep Hierarchical Variational Autoencoder

  Arash Vahdat (NVIDIA) · Jan Kautz (NVIDIA)

• Evidential Sparsification of Multimodal Latent Spaces in Conditional Variational Autoencoders

  Masha Itkina (Stanford University) · Boris Ivanovic (Stanford University) · Ransalu Senanayake (Stanford University) · Mykel J Kochenderfer (Stanford University) · Marco Pavone (Stanford University)

• Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernels

  Yi Zhou (University of Southern California) · Chenglei Wu (Facebook) · Zimo Li (University of Southern California) · Chen Cao (Snap Inc.) · Yuting Ye (Facebook Reality Labs) · Jason Saragih (Facebook) · Hao Li (Pinscreen/University of Southern California/USC ICT) · Yaser Sheikh (Facebook Reality Labs)

• Recursive Inference for Variational Autoencoders

  Minyoung Kim (Samsung AI Center Cambridge) · Vladimir Pavlovic (Rutgers University)

• 【看看other-2】 The Autoencoding Variational Autoencoder

  Taylan Cemgil (DeepMind) · Sumedh Ghaisas (DeepMind) · Krishnamurthy Dvijotham (DeepMind) · Sven Gowal (DeepMind) · Pushmeet Kohli (DeepMind)

• Autoencoders that don’t overfit towards the Identity

  Harald Steck (Netflix)

clustering

• Deep Subspace Clustering with Data Augmentation

  Mahdi Abavisani (Rutgers, The State University of New Jersey) · Alireza Naghizadeh (Rutgers University) · Dimitris Metaxas (Rutgers University) · Vishal Patel (Johns Hopkins University)

• Bandit-PAM: Almost Linear Time k-Medoids Clustering via Multi-Armed Bandits

  Mo Tiwari (Stanford University) · Martin Zhang (Harvard University) · James J Mayclin (Stanford University) · Sebastian Thrun (Stanford University) · Chris Piech (Stanford) · Ilan Shomorony (University of Illinois at Urbana Champaign)

• Self-Supervised Learning by Cross-Modal Audio-Video Clustering

  Humam Alwassel (KAUST) · Dhruv Mahajan (Facebook) · Bruno Korbar (Facebook) · Lorenzo Torresani (Facebook AI) · Bernard Ghanem (KAUST) · Du Tran (Facebook AI)

• Near-Optimal Comparison Based Clustering

  Michaël Perrot (Max Planck Institute for Intelligent Systems) · Pascal Esser (Technical University of Munich) · Debarghya Ghoshdastidar (Technical University Munich)

• Graduated Assignment for Joint Multi-Graph Matching and Clustering with Application to Unsupervised Graph Matching Network Learning

  Runzhong Wang (Shanghai Jiao Tong University) · Junchi Yan (Shanghai Jiao Tong University) · Xiaokang Yang (Shanghai Jiao Tong University)

• Scalable Approximation Algorithm for Fair k−center Clustering

  Elfarouk Harb (Hong Kong University of Science and Technology) · Ho Shan Lam (The Hong Kong University of Science and Technology)

• Deep Transformation-Invariant Clustering

  Tom Monnier (École des ponts Paristech) · Thibault Groueix (École des ponts ParisTech) · Mathieu Aubry (École des ponts ParisTech)

• Efficient Clustering for Stretched Mixtures: Landscape and Optimality

  Kaizheng Wang (Columbia University) · Yuling Yan (Princeton University) · Mateo Diaz (Cornell University)

• Efficient Clustering Based On A Unified View Of K-means And Ratio-cut

  Shenfei Pei (Northwestern Polytechnical University) · Feiping Nie (University of Texas Arlington) · Rong Wang (Northwestern Polytechnical University) · Xuelong Li (Northwestern Polytechnical University)

• Adversarial Learning for Robust Deep Clustering

  Xu Yang (Xidian University) · Cheng Deng (Xidian University) · Kun Wei (Xidian University) · Junchi Yan (Shanghai Jiao Tong University) · Wei Liu (Tencent AI Lab)

• Sliding Window Algorithms for k-Clustering Problems

  Michele Borassi (Google Switzerland GmbH) · Alessandro Epasto (Google) · Silvio Lattanzi (Google Research) · Sergei Vassilvitskii (Google) · Morteza Zadimoghaddam (Google Research)

• From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering

  Ines Chami (Stanford University) · Albert Gu (Stanford) · Vaggos Chatziafratis (Stanford University, California) · Christopher Ré (Stanford)

• Probabilistic Fair Clustering

  Seyed Esmaeili (University of Maryland, College Park) · Brian Brubach (University of Maryland) · Leonidas Tsepenekas (University of Maryland) · John Dickerson (University of Maryland)

• Strongly local p-norm-cut algorithms for semi-supervised learning and local graph clustering

  Meng Liu (Purdue University) · David Gleich (Purdue University)

• Fair Hierarchical Clustering

  Sara Ahmadian (Google Research) · Alessandro Epasto (Google) · Marina Knittel (University of Maryland, College Park) · Ravi Kumar (Google) · Mohammad Mahdian (Google Research) · Benjamin Moseley (Carnegie Mellon University) · Philip Pham (Google) · Sergei Vassilvitskii (Google) · Yuyan Wang (Carnegie Mellon University)

• Partially View-aligned Clustering

  Zhenyu Huang (Sichuan University) · Peng Hu (Institute for Infocomm Research, ASTAR) · Joey Tianyi Zhou (IHPC, ASTAR) · Jiancheng Lv (Machine Intelligence Laboratory College of Computer Science, Sichuan University) · Xi Peng (Institute for Infocomm, Research Agency for Science, Technology and Research (A*STAR) Singapore)

• Differentially Private Clustering: Tight Approximation Ratios

  Badih Ghazi (Google) · Ravi Kumar (Google) · Pasin Manurangsi (Google)

• On the Power of Louvain for Graph Clustering

  Vincent Cohen-Addad (CNRS & Sorbonne Université) · Adrian Kosowski (NavAlgo) · Frederik Mallmann-Trenn (King’s College London) · David Saulpic (Ecole normale supérieure)

• SMYRF - Efficient attention using asymmetric clustering

  Giannis Daras (National Technical University of Athens) · Nikita Kitaev (University of California, Berkeley) · Augustus Odena (Google Brain) · Alexandros Dimakis (University of Texas, Austin)

• Higher-Order Spectral Clustering of Directed Graphs

  Valdimar Steinar Ericsson Laenen (FiveAI) · He Sun (School of Informatics, The University of Edinburgh)

data augmentation

• Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness

  Long Zhao (Rutgers University) · Ting Liu (Google) · Xi Peng (University of Delaware) · Dimitris Metaxas (Rutgers University)

• A Group-Theoretic Framework for Data Augmentation

  Shuxiao Chen (University of Pennsylvania) · Edgar Dobriban (University of Pennsylvania) · Jane Lee (University of Pennsylvania)

• Post-training Iterative Hierarchical Data Augmentation for Deep Networks

  Adil Khan (Innopolis University) · Khadija Fraz (Hazara University)

• Heavy-tailed Representations, Text Polarity Classification & Data Augmentation

  Hamid JALALZAI (Télécom ParisTech) · Pierre Colombo (Telecom ParisTech) · Chloé Clavel (Telecom-ParisTech, Paris, France) · Eric Gaussier (Université Joseph Fourier, Grenoble) · Giovanna Varni (Telecom ParisTec) · Emmanuel Vignon (IBM) · Anne Sabourin (LTCI, Telecom ParisTech, Université Paris-Saclay)

• Unsupervised Data Augmentation for Consistency Training

  Qizhe Xie (CMU, Google Brain) · Zihang Dai (Carnegie Mellon University) · Eduard Hovy (CMU) · Thang Luong (Google Brain) · Quoc V Le (Google)

• Exemplar VAEs for Exemplar based Generation and Data Augmentation

  Sajad Norouzi (University of Toronto / Vector Institute) · David J Fleet (University of Toronto) · Mohammad Norouzi (Google Brain)

• Practical automated data augmentation with a reduced search space

  Ekin Dogus Cubuk (Google Brain) · Barret Zoph (Google Brain) · Jon Shlens (Google Research) · Quoc V Le (Google)

• Counterfactual Data Augmentation using Locally Factored Dynamics

  Silviu Pitis (University of Toronto) · Elliot Creager (University of Toronto) · Animesh Garg (Univ. of Toronto, Vector Institute, Nvidia)

• Deep Subspace Clustering with Data Augmentation

  Mahdi Abavisani (Rutgers, The State University of New Jersey) · Alireza Naghizadeh (Rutgers University) · Dimitris Metaxas (Rutgers University) · Vishal Patel (Johns Hopkins University)

有点意思

• Learning Loss for Test-Time Augmentation

  Ildoo Kim (Kakao Brain) · Younghoon Kim (Sungshin Women’s University) · Sungwoong Kim (Kakao Brain)

• Predicting Training Time Without Training

  Luca Zancato (University of Padova) · Alessandro Achille (Amazon Web Services) · Avinash Ravichandran (AWS) · Rahul Bhotika (Amazon) · Stefano Soatto (UCLA)