Spotlight

TitleAuthors
Machine Learning Estimation of Heterogeneous Treatment Effects with InstrumentsVasilis Syrgkanis · Victor Lei · Miruna Oprescu · Maggie Hei · Keith Battocchi · Greg Lewis
On Exact Computation with an Infinitely Wide Neural NetSanjeev Arora · Simon Du · Wei Hu · Zhiyuan Li · Russ Salakhutdinov · Ruosong Wang
List-decodable Linear RegressionSushrut Karmalkar · Adam Klivans · Pravesh Kothari
Legendre Memory Units: Continuous-Time Representation in Recurrent Neural NetworksAaron Voelker · Ivana Kajić · Chris Eliasmith
Identification of Conditional Causal Effects under Markov EquivalenceAmin Jaber · Jiji Zhang · Elias Bareinboim
Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural NetworksYuan Cao · Quanquan Gu
On the Hardness of Robust ClassificationPascale Gourdeau · Varun Kanade · Marta Kwiatkowska · James Worrell
Point-Voxel CNN for Efficient 3D Deep LearningZhijian Liu · Haotian Tang · Yujun Lin · Song Han
Likelihood-Free Overcomplete ICA and Applications In Causal DiscoveryChenwei DING · Mingming Gong · Kun Zhang · Dacheng Tao
Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural NetworksMahyar Fazlyab · Alexander Robey · Hamed Hassani · Manfred Morari · George Pappas
Adversarial Examples Are Not Bugs, They Are FeaturesAndrew Ilyas · Shibani Santurkar · Dimitris Tsipras · Logan Engstrom · Brandon Tran · Aleksander Madry
Neural Networks with Cheap Differential OperatorsTian Qi Chen · David Duvenaud
Perceiving the arrow of time in autoregressive motionKristof Meding · Dominik Janzing · Bernhard Schölkopf · Felix A. Wichmann
Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural NetworksYuanzhi Li · Colin Wei · Tengyu Ma
Empirically Measuring Concentration: Fundamental Limits on Intrinsic RobustnessSaeed Mahloujifar · Xiao Zhang · Mohammad Mahmoody · David Evans
Sequential Neural ProcessesGautam Singh · Jaesik Yoon · Youngsung Son · Sungjin Ahn
Conditional Independence Testing using Generative Adversarial NetworksAlexis Bellot · Mihaela van der Schaar
Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz AugmentationColin Wei · Tengyu Ma
Quantum Entropy Scoring for Fast Robust Mean Estimation and Improved Outlier DetectionYihe Dong · Samuel Hopkins · Jerry Li
Deep Equilibrium ModelsShaojie Bai · J. Zico Kolter · Vladlen Koltun
Imitation Learning from Observations by Minimizing Inverse Dynamics DisagreementChao Yang · Xiaojian Ma · Wenbing Huang · Fuchun Sun · Huaping Liu · Junzhou Huang · Chuang Gan
Learning Hierarchical Priors in VAEsAlexej Klushyn · Nutan Chen · Richard Kurle · Botond Cseke · Patrick van der Smagt
Asymmetric Valleys: Beyond Sharp and Flat Local MinimaHaowei He · Gao Huang · Yang Yuan
Scalable Global Optimization via Local Bayesian OptimizationDavid Eriksson · Michael Pearce · Jacob Gardner · Ryan Turner · Matthias Poloczek
Learning to Control Self-Assembling Morphologies: A Study of Generalization via ModularityDeepak Pathak · Christopher Lu · Trevor Darrell · Phillip Isola · Alexei Efros
Implicit Generation and Modeling with Energy Based ModelsYilun Du · Igor Mordatch
Reducing the variance in online optimization by transporting past gradientsSébastien Arnold · Pierre-Antoine Manzagol · Reza Babanezhad Harikandeh · Ioannis Mitliagkas · Nicolas Le Roux
Uncertainty on Asynchronous Time Event PredictionMarin Biloš · Bertrand Charpentier · Stephan Günnemann
A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement LearningNicolas Carion · Nicolas Usunier · Gabriel Synnaeve · Alessandro Lazaric
Invertible Convolutional FlowMahdi Karami · Dale Schuurmans · Jascha Sohl-Dickstein · Laurent Dinh · Daniel Duckworth
Who is Afraid of Big Bad Minima? Analysis of gradient-flow in spiked matrix-tensor modelsStefano Sarao Mannelli · Giulio Biroli · Chiara Cammarota · Florent Krzakala · Lenka Zdeborová
Bayesian Optimization under Heavy-tailed PayoffsSayak Ray Chowdhury · Aditya Gopalan
Learning Compositional Neural Programs with Recursive Tree Search and PlanningThomas PIERROT · Guillaume Ligner · Scott Reed · Olivier Sigaud · Nicolas Perrin · Alexandre Laterre · David Kas · Karim Beguir · Nando de Freitas
Residual Flows for Invertible Generative ModelingTian Qi Chen · Jens Behrmann · David Duvenaud · Joern-Henrik Jacobsen
Fast and Provable ADMM for Learning with Generative PriorsFabian Latorre · Armin eftekhari · Volkan Cevher
Variational Bayesian Optimal Experimental DesignAdam Foster · Martin Jankowiak · Elias Bingham · Paul Horsfall · Yee Whye Teh · Thomas Rainforth · Noah Goodman
Guided Meta-Policy SearchRussell Mendonca · Abhishek Gupta · Rosen Kralev · Pieter Abbeel · Sergey Levine · Chelsea Finn
Dual Variational Generation for Low Shot Heterogeneous Face RecognitionChaoyou Fu · Xiang Wu · Yibo Hu · Huaibo Huang · Ran He
Complexity of Highly Parallel Non-Smooth Convex OptimizationSebastien Bubeck · Qijia Jiang · Yin-Tat Lee · Yuanzhi Li · Aaron Sidford
Implicit Posterior Variational Inference for Deep Gaussian ProcessesHaibin YU · Yizhou Chen · Bryan Kian Hsiang Low · Patrick Jaillet · Zhongxiang Dai
Better Exploration with Optimistic Actor CriticKamil Ciosek · Quan Vuong · Robert Loftin · Katja Hofmann
Adaptive Density Estimation for Generative ModelsThomas Lucas · Konstantin Shmelkov · Karteek Alahari · Cordelia Schmid · Jakob Verbeek
SySCD: A System-Aware Parallel Coordinate Descent AlgorithmNikolas Ioannou · Celestine Mendler-Dünner · Thomas Parnell
Divide and Couple: Using Monte Carlo Variational Objectives for Posterior ApproximationJustin Domke · Daniel Sheldon
Robust exploration in linear quadratic reinforcement learning Jack Umenberger · Mina Ferizbegovic · Thomas Schön · Håkan Hjalmarsson
Twin Auxilary Classifiers GANMingming Gong · Yanwu Xu · Chunyuan Li · Kun Zhang · Kayhan Batmanghelich
Learning Positive Functions with Pseudo Mirror DescentYingxiang Yang · Haoxiang Wang · Negar Kiyavash · Niao He
The Randomized Midpoint Method for Log-Concave SamplingRuoqi Shen · Yin Tat Lee
Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy PoliciesYonathan Efroni · Nadav Merlis · Mohammad Ghavamzadeh · Shie Mannor
Adversarial Fisher Vectors for Unsupervised Representation LearningJoshua Susskind · Shuangfei Zhai · Walter Talbott · Carlos Guestrin
UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained OptimizationAli Kavis · Kfir Y. Levy · Francis Bach · Volkan Cevher
Poisson-Minibatching for Gibbs Sampling with Convergence Rate GuaranteesRuqi Zhang · Christopher De Sa
Hindsight Credit AssignmentAnna Harutyunyan · Will Dabney · Thomas Mesnard · Mohammad Gheshlaghi Azar · Bilal Piot · Nicolas Heess · Hado van Hasselt · Gregory Wayne · Satinder Singh · Doina Precup · Remi Munos
Emergence of Object Segmentation in Perturbed Generative ModelsAdam Bielski · Paolo Favaro
Sinkhorn Barycenters with Free Support via Frank-Wolfe AlgorithmGiulia Luise · Saverio Salzo · Massimiliano Pontil · Carlo Ciliberto
Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic RatesAdil SALIM · Dmitry Koralev · Peter Richtarik
Weight Agnostic Neural NetworksAdam Gaier · David Ha
Compression with Flows via Local Bits-Back CodingJonathan Ho · Evan Lohn · Pieter Abbeel
Learning dynamic polynomial proofsAlhussein Fawzi · Mateusz Malinowski · Hamza Fawzi · Omar Fawzi
Stochastic Runge-Kutta Accelerates Langevin Monte Carlo and BeyondXuechen Li · Yi Wu · Lester Mackey · Murat Erdogdu
Calibration tests in multi-class classification: A unifying frameworkDavid Widmann · Fredrik Lindsten · Dave Zachariah
A Condition Number for Joint Optimization of Cycle-Consistent NetworksLeonidas J Guibas · Qixing Huang · Zhenxiao Liang
DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution CorrectionsOfir Nachum · Yinlam Chow · Bo Dai · Lihong Li
Sparse Logistic Regression Learns All Discrete Pairwise Graphical ModelsShanshan Wu · Sujay Sanghavi · Alexandros Dimakis
Verified Uncertainty CalibrationAnanya Kumar · Percy Liang · Tengyu Ma
Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive ConvolutionThang Vu · Hyunjun Jang · Trung X. Pham · Chang Yoo
VIREL: A Variational Inference Framework for Reinforcement LearningMatthew Fellows · Anuj Mahajan · Tim G. J. Rudner · Shimon Whiteson
Fast Convergence of Belief Propagation to Global Optima: Beyond Correlation Decay Frederic Koehler
Fast structure learning with modular regularizationGreg Ver Steeg · Hrayr Harutyunyan · Daniel Moyer · Aram Galstyan
Probabilistic Watershed: Sampling all spanning forests for seeded segmentation and semi-supervised learningEnrique Fita Sanmartin · Sebastian Damrich · Fred Hamprecht
Unsupervised Curricula for Visual Meta-Reinforcement LearningAllan Jabri · Kyle Hsu · Abhishek Gupta · Ben Eysenbach · Sergey Levine · Chelsea Finn
Smoothing Structured Decomposable CircuitsAndy Shih · Guy Van den Broeck · Paul Beame · Antoine Amarilli
Principal Component Projection and Regression in Nearly Linear Time through Asymmetric SVRGYujia Jin · Aaron Sidford
DM2C: Deep Mixed-Modal ClusteringYangbangyan Jiang · Qianqian Xu · Zhiyong Yang · Xiaochun Cao · Qingming Huang
Policy Continuation with Hindsight Inverse DynamicsHao Sun · Zhizhong Li · Xiaotong Liu · Bolei Zhou · Dahua Lin
Counting the Optimal Solutions in Graphical ModelsRadu Marinescu · Rina Dechter
PIDForest: Anomaly Detection via Partial IdentificationParikshit Gopalan · Vatsal Sharan · Udi Wieder
Learning Object Bounding Boxes for 3D Instance Segmentation on Point CloudsBo Yang · Jianan Wang · Ronald Clark · Qingyong Hu · Sen Wang · Andrew Markham · Niki Trigoni
Learning Reward Machines for Partially Observable Reinforcement LearningRodrigo Toro Icarte · Ethan Waldie · Toryn Klassen · Rick Valenzano · Margarita Castro · Sheila McIlraith
Combining Generative and Discriminative Models for Hybrid InferenceVictor Garcia Satorras · Max Welling · Zeynep Akata
Fast and Flexible Multi-Task Classification using Conditional Neural Adaptive ProcessesJames Requeima · Jonathan Gordon · John Bronskill · Sebastian Nowozin · Richard Turner
Time/Accuracy Tradeoffs for Learning a ReLU with respect to Gaussian MarginalsSurbhi Goel · Sushrut Karmalkar · Adam Klivans
Are sample means in multi-armed bandits positively or negatively biased? Jaehyeok Shin · Aaditya Ramdas · Alessandro Rinaldo
Finding Friend and Foe in Multi-Agent GamesJack Serrino · Max Kleiman-Weiner · David Parkes · Josh Tenenbaum
Multimodal Model-Agnostic Meta-Learning via Task-Aware ModulationRisto Vuorio · Shao-Hua Sun · Hexiang Hu · Joseph Lim
Limitations of Lazy Training of Two-layers Neural NetworkSong Mei · Theodor Misiakiewicz · Behrooz Ghorbani · Andrea Montanari
SIC-MMAB: Synchronisation Involves Communication in Multiplayer Multi-Armed BanditsEtienne Boursier · Vianney Perchet
Efficient Regret Minimization Algorithm for Extensive-Form Correlated EquilibriumGabriele Farina · Chun Kai Ling · Fei Fang · Tuomas Sandholm
Efficient Meta Learning via Minibatch Proximal UpdatePan Zhou · Xiaotong Yuan · Huan Xu · Shuicheng Yan · Jiashi Feng
Generalization Bounds for Neural Networks via Approximate Description LengthAmit Daniely · Elad Granot
Recovering BanditsCiara Pike-Burke · Steffen Grunewalder
Poincaré Recurrence, Cycles and Spurious Equilibria in Gradient-Descent-Ascent for Non-Convex Non-Concave Zero-Sum GamesEmmanouil-Vasileios Vlatakis-Gkaragkounis · Lampros Flokas · Georgios Piliouras
Reconciling meta-learning and continual learning with online mixtures of tasksGhassen Jerfel · Erin Grant · Tom Griffiths · Katherine Heller
Small ReLU networks are powerful memorizers: a tight analysis of memorization capacityChulhee Yun · Suvrit Sra · Ali Jadbabaie
Model Selection for Contextual BanditsDylan Foster · Akshay Krishnamurthy · Haipeng Luo
Multiagent Evaluation under Incomplete InformationMark Rowland · Shayegan Omidshafiei · Karl Tuyls · Julien Perolat · Michal Valko · Georgios Piliouras · Remi Munos
Learning by Abstraction: The Neural State MachineDrew Hudson · Christopher Manning
Cold Case: The Lost MNIST DigitsChhavi Yadav · Leon Bottou
Beyond Online Balanced Descent: An Optimal Algorithm for Smoothed Online OptimizationGautam Goel · Yiheng Lin · Haoyuan Sun · Adam Wierman
Graph-based Discriminators: Sample Complexity and ExpressivenessRoi Livni · Yishay Mansour
Heterogeneous Graph Learning for Visual Commonsense ReasoningWeijiang Yu · Jingwen Zhou · Weihao Yu · Xiaodan Liang · Nong Xiao
An adaptive nearest neighbor rule for classificationAkshay Balsubramani · Sanjoy Dasgupta · yoav Freund · Shay Moran
Learning in Generalized Linear Contextual Bandits with Stochastic DelaysZhengyuan Zhou · Renyuan Xu · Jose Blanchet
Nearly Tight Bounds for Robust Proper Learning of Halfspaces with a MarginIlias Diakonikolas · Daniel Kane · Pasin Manurangsi
Self-Critical Reasoning for Robust Visual Question AnsweringJialin Wu · Raymond Mooney
Multilabel reductions: what is my loss optimising?Aditya Menon · Ankit Singh Rawat · Sashank Reddi · Sanjiv Kumar
Optimal Stochastic and Online Learning with Individual IteratesYunwen Lei · Peng Yang · Ke Tang · Ding-Xuan Zhou
McDiarmid-Type Inequalities for Graph-Dependent Variables and Stability BoundsRui (Ray) Zhang · Xingwu Liu · Yuyi Wang · Liwei Wang
SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding SystemsAlex Wang · Yada Pruksachatkun · Nikita Nangia · Amanpreet Singh · Julian Michael · Felix Hill · Omer Levy · Samuel Bowman
Optimal Sparse Decision TreesXiyang Hu · Cynthia Rudin · Margo Seltzer
Online Learning via the Differential Privacy LensJacob Abernethy · Young Hun Jung · Chansoo Lee · Audra McMillan · Ambuj Tewari
The Broad Optimality of Profile Maximum LikelihoodYi Hao · Alon Orlitsky
Implicit Regularization in Deep Matrix FactorizationSanjeev Arora · Nadav Cohen · Wei Hu · Yuping Luo
Learning Perceptual Inference by ContrastingChi Zhang · Baoxiong Jia · Feng Gao · Yixin Zhu · HongJing Lu · Song-Chun Zhu
Provably Robust Deep Learning via Adversarially Trained Smoothed ClassifiersHadi Salman · Jerry Li · Ilya Razenshteyn · Pengchuan Zhang · Huan Zhang · Sebastien Bubeck · Greg Yang
Modeling Conceptual Understanding in Image Reference GamesRodolfo Corona Rodriguez · Stephan Alaniz · Zeynep Akata
SGD on Neural Networks Learns Functions of Increasing ComplexityDimitris Kalimeris · Gal Kaplun · Preetum Nakkiran · Benjamin Edelman · Tristan Yang · Boaz Barak · Haofeng Zhang
Universality and individuality in neural dynamics across large populations of recurrent networksNiru Maheswaranathan · Alex Williams · Matthew Golub · Surya Ganguli · David Sussillo
Adversarial Music: Real world Audio Adversary against Wake-word Detection SystemJuncheng Li · Shuhui Qu · Xinjian Li · Joseph Szurley · J. Zico Kolter · Florian Metze
This Looks Like That: Deep Learning for Interpretable Image RecognitionChaofan Chen · Oscar Li · Daniel Tao · Alina Barnett · Cynthia Rudin · Jonathan K Su
When does label smoothing help?Rafael Müller · Simon Kornblith · Geoffrey E Hinton
Better Transfer Learning with Inferred Successor MapsTamas Madarasz · Tim Behrens
Convergence of Adversarial Training in Overparametrized Neural NetworksRuiqi Gao · Tianle Cai · Haochuan Li · Cho-Jui Hsieh · Liwei Wang · Jason Lee
Assessing Social and Intersectional Biases in Contextualized Word RepresentationsYi Chern Tan · L. Elisa Celis
Splitting Steepest Descent for Growing Neural Architectures Lemeng Wu · Dilin Wang · Qiang Liu
A unified theory for the origin of grid cells through the lens of pattern formationBen Sorscher · Gabriel Mel · Surya Ganguli · Samuel Ocko
Adversarial Training and Robustness for Multiple PerturbationsFlorian Tramer · Dan Boneh
Paradoxes in Fair Machine LearningPaul Goelz · Anson Kahng · Ariel Procaccia
Positional NormalizationBoyi Li · Felix Wu · Kilian Weinberger · Serge Belongie
Infra-slow brain dynamics as a marker for cognitive function and declineShagun Ajmera Shyam Sunder Ajmera · Shreya Rajagopal · Razi Rehman · Devarajan Sridharan
Zero-shot Knowledge Transfer via Adversarial Belief MatchingPaul Micaelli · Amos Storkey
Multi-Criteria Dimensionality Reduction with Applications to FairnessUthaipon Tantipongpipat · Samira Samadi · Mohit Singh · Jamie Morgenstern · Santosh Vempala
Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein DistanceKimia Nadjahi · Alain Durmus · Umut Simsekli · Roland Badeau
Ask not what AI can do, but what AI should do: Towards a framework of task delegabilityBrian Lubars · Chenhao Tan
On the Downstream Performance of Compressed Word EmbeddingsAvner May · Jian Zhang · Tri Dao · Christopher Ré
A Nonconvex Approach for Exact and Efficient Multichannel Sparse Blind DeconvolutionQing Qu · Xiao Li · Zhihui Zhu
Theoretical Analysis of Adversarial Learning: A Minimax ApproachZhuozhuo Tu · Jingwei Zhang · Dacheng Tao
Making AI Forget You: Data Deletion in Machine LearningAntonio Ginart · Melody Guan · Gregory Valiant · James Zou
CPM-Nets: Cross Partial Multi-View NetworksChangqing Zhang · Zongbo Han · yajie cui · Huazhu Fu · Joey Tianyi Zhou · Qinghua Hu
Efficiently Learning Fourier Sparse Set FunctionsAndisheh Amrollahi · Amir Zandieh · Michael Kapralov · Andreas Krause
Statistical bounds for entropic optimal transport: sample complexity and the central limit theoremGonzalo Mena · Jonathan Niles-Weed
On Testing for Biases in Peer ReviewIvan Stelmakh · Nihar Shah · Aarti Singh
Numerically Accurate Hyperbolic Embeddings Using Tiling-Based ModelsTao Yu · Christopher De Sa
Generalization Error Analysis of Quantized Compressive LearningXiaoyun Li · Ping Li
Differentiable Ranking and Sorting using Optimal TransportMarco Cuturi · Olivier Teboul · Jean-Philippe Vert
A Step Toward Quantifying Independently Reproducible Machine Learning ResearchEdward Raff
Large Memory Layers with Product KeysGuillaume Lample · Alexandre Sablayrolles · Marc'Aurelio Ranzato · Ludovic Denoyer · Herve Jegou
Surfing: Iterative Optimization Over Incrementally Trained Deep NetworksGanlin Song · Zhou Fan · John Lafferty
KerGM: Kernelized Graph MatchingZhen Zhang · Yijian Xiang · Lingfei Wu · Bing Xue · Arye Nehorai
Private Learning Implies Online Learning: An Efficient ReductionAlon Gonen · Elad Hazan · Shay Moran
Cross-lingual Language Model PretrainingAlexis CONNEAU · Guillaume Lample
Quadratic Video InterpolationXiangyu Xu · Li Siyao · Wenxiu Sun · Qian Yin · Ming-Hsuan Yang
Wasserstein Weisfeiler-Lehman Graph KernelsMatteo Togninalli · Elisabetta Ghisu · Felipe Llinares-López · Bastian Rieck · Karsten Borgwardt
Private Stochastic Convex Optimization with Optimal RatesRaef Bassily · Vitaly Feldman · Kunal Talwar · Abhradeep Guha Thakurta
N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to MoleculesShengchao Liu · Mehmet F Demirel · Yingyu Liang
Training Image Estimators without Image Ground TruthZhihao Xia · Ayan Chakrabarti
Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced KernelColin Wei · Jason Lee · Qiang Liu · Tengyu Ma
Practical Differentially Private Top-k Selection with Pay-what-you-get CompositionDavid Durfee · Ryan Rogers
Evaluating Protein Transfer Learning with TAPERoshan Rao · Nicholas Bhattacharya · Neil Thomas · Yan Duan · Peter Chen · John Canny · Pieter Abbeel · Yun Song
STREETS: A Novel Camera Network Dataset for Traffic FlowCorey Snyder · Minh Do
Comparing distributions: $\ell_1$ geometry improves kernel two-sample testingmeyer scetbon · Gael Varoquaux
Differentially Private Markov Chain Monte CarloMikko Heikkilä · Joonas Jälkö · Onur Dikmen · Antti Honkela
Cormorant: Covariant Molecular Neural NetworksBrandon Anderson · Truong Son Hy · Risi Kondor
Reflection Separation using a Pair of Unpolarized and Polarized ImagesYouwei Lyu · Zhaopeng Cui · Si Li · Marc Pollefeys · Boxin Shi