[AISTATS Logo]
AISTATS 2017

AISTATS 2017 Accepted Papers

Any typos will be corrected in the final list of proceedings. This is a temporary list in alphabetical order of the title. To address serious typos, please contact publicity chair Aaditya Ramdas at aramdas [at] berkeley.edu.

A Fast and Scalable Joint Estimator for Learning Multiple Related Sparse Gaussian Graphical Models
Beilun Wang, Ji Gao, Yanjun Qi

A Framework for Optimal Matching for Causal Inference
Nathan Kallus

A Learning Theory of Ranking Aggregation
Anna KORBA, Stéphan Clemençon, Eric Sibony

A Lower Bound on the Partition Function of Attractive Graphical Models in the Continuous Case
Nicholas Ruozzi

A Maximum Matching Algorithm for Basis Selection in Spectral Learning
Ariadna Quattoni, Xavier Carreras, Matthias Gallé

A New Class of Private Chi-Square Hypothesis Tests
Ryan Rogers, Daniel Kifer

A Stochastic Nonconvex Splitting Method for Symmetric Nonnegative Matrix Factorization
Songtao Lu, Mingyi Hong, Zhengdao Wang

A Sub-Quadratic Exact Medoid Algorithm
James Newling, Francois Fleuret

A Unified Computational and Statistical Framework for Nonconvex Low-rank Matrix Estimation
Lingxiao Wang, Xiao Zhang, Quanquan Gu

A Unified Optimization View on Generalized Matching Pursuit and Frank-Wolfe
Francesco Locatello, Rajiv Khanna, Michael Tschannen, Martin Jaggi

Active Positive Semidefinite Matrix Completion: Algorithms, Theory and Applications
Aniruddha Bhargava, Ravi Ganti, Rob Nowak

Adaptive ADMM with Spectral Penalty Parameter Selection
Zheng Xu, Mario Figueiredo, Tom Goldstein

An Information-Theoretic Route from Generalization in Expectation to Generalization in Probability
Ibrahim Alabdulmohsin

Annular Augmentation Sampling
Francois Fagan, Jalaj Bhandari, John Cunningham

Anomaly Detection in Extreme Regions via Empirical MV-sets on the Sphere
Albert Thomas, Stéphan Clemençon, Alexandre Gramfort, Anne Sabourin

ASAGA: Asynchronous Parallel SAGA
Rémi Leblond, Fabian Pedregosa, Simon Lacoste-Julien

Asymptotically exact inference in likelihood-free models
Matthew Graham, Amos Storkey

Attributing Hacks
Ziqi Liu, Alex Smola, Kyle Soska, Yu-Xiang Wang, Qinghua Zheng

Automated Inference with Adaptive Batches
Soham De, Abhay Yadav, David Jacobs, Tom Goldstein

Bayesian Hybrid Matrix Factorisation for Data Integration
Thomas Brouwer, Pietro Lio

Belief Propagation in Conditional RBMs for Structured Prediction
Wei Ping, Alex Ihler

Beta calibration: a well-founded and easily implemented improvement on logistic calibration for binary classifiers
Meelis Kull, Telmo de Menezes e Silva Filho, Peter Flach

Binary and Multi-Bit Coding for Stable Random Projections
Ping Li

Black-box Importance Sampling
Qiang Liu, Jason Lee

Clustering from Multiple Uncertain Experts
Yale Chang, Junxiang Chen, Michael Cho, Peter Castaldi, Ed Silverman, Jennifer Dy

Co-Occuring Directions Sketching for Approximate Matrix Multiply
Youssef Mroueh, Etienne Marcheret, Vaibahava Goel

Combinatorial Topic Models using Small-Variance Asymptotics
Ke Jiang, Suvrit Sra, Brian Kulis

Communication-efficient Distributed Sparse Linear Discriminant Analysis
Lu Tian, Quanquan Gu

Communication-Efficient Learning of Deep Networks from Decentralized Data
Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, Blaise Aguera y Arcas

Comparison Based Nearest Neighbor Search
Siavash Haghiri, Ulrike von Luxburg, Debarghya Ghoshdastidar

Complementary Sum Sampling for Likelihood Approximation in Large Scale Classification
David Barber, Aleksandar Botev, Bowen Zheng

Compressed Least Squares Regression revisited
Martin Slawski

Conditions beyond treewidth for tightness of higher-order LP relaxations
Mark Rowland, Aldo Pacchiano, Adrian Weller

Conjugate-Computation Variational Inference : Converting Variational Inference in Non-Conjugate Models to Inferences in Conjugate Models
Mohammad Khan, Wu Lin

Consistent and Efficient Nonparametric Different-Feature Selection
Satoshi Hara, Takayuki Katsuki, Hiroki Yanagisawa, Takafumi Ono, Ryo Okamoto, Shigeki Takeuchi

Contextual Bandits with Latent Confounders: An NMF Approach
Rajat Sen, Karthikeyan Shanmugam, Murat Kocaoglu, Alex Dimakis, Sanjay Shakkottai

Convergence rate of stochastic k-means
Cheng Tang, Claire Monteleoni

ConvNets with Smooth Adaptive Activation Functions for Regression
Le Hou, Dimitris Samaras, Tahsin Kurc, Yi Gao, Joel Saltz

CPSG-MCMC: Clustering-Based Preprocessing method for Stochastic Gradient MCMC
Tianfan Fu, Zhihua Zhang

Data Driven Resource Allocation for Distributed Learning
Travis Dick, Venkata Krishna Pillutla, Mu Li, Colin White, Nina Balcan, Alex Smola

Decentralized Collaborative Learning of Personalized Models over Networks
Paul Vanhaesebrouck, Aurélien Bellet, Marc Tommasi

Detecting Dependencies in High-Dimensional, Sparse Databases Using Probabilistic Programming and Non-parametric Bayes
Feras Saad, Vikash Mansinghka

Discovering and Exploiting Additive Structure for Bayesian Optimization
Jacob Gardner, Chuan Guo, Kilian Weinberger, Roman Garnett, Roger Grosse

Distance Covariance Analysis
Benjamin Cowley, Joao Semedo, Amin Zandvakili, Adam Kohn, Matthew Smith, Byron Yu

Distributed Sequential Sampling for Kernel Matrix Approximation
Daniele Calandriello, Alessandro Lazric, Michal Valko

Distribution of Gaussian Process Arc Lengths
Justin Bewsher, Alessandra Tosi, Michael Osborne, Stephen Roberts

Diversity Leads to Generalization in Neural Networks
Bo Xie, Yingyu Liang, Le Song

DP-EM: Differentially Private Expectation Maximization
Mijung Park, James Foulds, Kamalika Choudhary, Max Welling

Dynamic Collaborative Filtering With Compound Poisson Factorization
Ghassen Jerfel, Basbug, Barbara Engelhardt

Efficient Algorithm for Sparse Tensor-variate Gaussian Graphical Models via Gradient Descent
Pan Xu, Quanquan Gu

Efficient Multiclass Prediction on Graphs via Surrogate Losses
Alexander Rakhlin, Karthik Sridharan

Efficient Rank Aggregation via Lehmer Codes
Pan Li, Arya Mazumdar, Olgica Milenkovic

Encrypted accelerated least squares regression
Pedro Esperanca, Louis Aslett, Chris Holmes

Estimating Density Ridges by Direct Estimation of Density-Derivative-Ratios
Hiroaki Sasaki, Takafumi Kanamori, Masashi Sugiyama

Exploration--Exploitation in MDPs with Options
Ronan Fruit, Alessandro Lazric

Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets
Aaron Klein, Stefan Falkner, Simon Bartels, Philipp Hennig, Frank Hutter

Fast Classification with Binary Prototypes
Kai Zhong, Ruiqi Guo, Sanjiv Kumar, Bowei Yan, David Simcha, Inderjit Dhillon

Fast column generation for atomic norm regularization.
Marina Vinyes, Guillaume Obozinski

Fast rates with high probability in exp-concave statistical learning
Nishant Mehta

Faster Coordinate Descent via Adaptive Importance Sampling
Dmytro Perekrestenko, Volkan Cevher, Martin Jaggi

Finite-sum Composition Optimization via Variance Reduced Gradient Descent
Xiangru Lian, Ji Liu, Mengdi Wang

Linking Micro Event History to Macro Prediction in Point Process Models
Yichen Wang, Xiaojing Ye, Haomin Zhou, Hongyuan Zha, Le Song

Frank-Wolfe Algorithms for Saddle Point Problems
Gauthier Gidel, Simon Lacoste-Julien, Tony Jebara

Frequency Domain Predictive Modelling with Aggregated Data
Avradeep Bhowmik, Joydeep Ghosh, Oluwasanmi Koyejo

Generalization Error of Invariant Classifiers
Jure Sokolic, Raja Giryes, Guillermo Sapiro, Miguel Rodrigues

Generalized Pseudolikelihood Methods for Inverse Covariance Estimation
Alnur Ali, Kshitij Khare, Sang-Yun Oh, Bala Rajaratnam

Global Convergence of Non-Convex Gradient Descent for Computing Matrix Squareroot
Prateek Jain, Chi Jin, Sham Kakade, Praneeth Netrapalli

Gradient Boosting on Stochastic Data Streams
Hanzhang Hu, Andrew Bagnell, Wen Sun, Martial Hebert, Arun Venkatraman

Gray-box inference for structured Gaussian process models
Pietro Galliani, Amir Dezfouli, Edwin Bonilla, Novi Quadrianto

Greedy Direction Method of Multiplier for MAP Inference of Large Output Domain
Xiangru Huang, Ian En-Hsu Yen, Ruohan Zhang, Qixing Huang, Pradeep Ravikumar, Inderjit Dhillon

Guaranteed Non-convex Optimization: Submodular Maximization over Continuous Domains
Andrew An Bian, Baharan Mirzasoleiman, Joachim Buhmann, Andreas Krause

Hierarchically-partitioned Gaussian Process Approximation
Byung-Jun Lee, Jongmin Lee, Kee-Eung Kim

High-dimensional Time Series Clustering via Cross-Predictability
Dezhi Hong, Quanquan Gu, Kamin Whitehouse

Hit-and-Run for Sampling and Planning in Non-Convex Spaces
Yasin Abbasi-Yadkori, Alan Malek, Peter Bartlett, Victor Gabillon

Horde of Bandits using Gaussian Markov Random Fields
Sharan Vaswani, Mark Schmidt, Laks Lakshmanan

Identifying groups of strongly correlated variables through Smoothed Ordered Weighted L_1-norms
Raman Sankaran, Francis Bach, Chiranjib Bhattacharya

Improved Strongly Adaptive Online Learning using Coin Betting
Kwang-Sung Jun, Rebecca Willett, Stephen Wright, Francesco Orabona

Inference Compilation and Universal Probabilistic Programming
Tuan Anh Le, Atilim Gunes Baydin, Frank Wood

Information Projection and Approximate Inference for Structured Sparse Variables
Rajiv Khanna, Joydeep Ghosh, Rusell Poldrack, Oluwasanmi Koyejo

Information-theoretic limits of Bayesian network structure learning
Asish Ghoshal, Jean Honorio

Initialization and Coordinate Optimization for Multi-way Matching
Da Tang, Tony Jebara

Label Filters for Large Scale Multilabel Classification
Alexandru Niculescu-Mizil, Ehsan Abbasnejad

Large-Scale Data-Dependent Kernel Approximation
Alin Popa, Catalin Ionescu, Cristian Sminchisescu

Learning Cost-Effective Treatment Regimes using Markov Decision Processes
Himabindu Lakkaraju, Cynthia Rudin

Learning from Conditional Distributions via Dual Kernel Embeddings
Bo Dai, Niao He, Yunpeng Pan, Byron Boots, Le Song

Learning Graphical Games from Behavioral Data: Sufficient and Necessary Conditions
Asish Ghoshal, Jean Honorio

Learning Nash Equilibrium for General-Sum Markov Games from Batch Data
Julien Perolat, Florian Strub, Bilal Piot, Olivier Pietquin

Learning Nonparametric Forest Graphical Models with Prior Information
Yuancheng Zhu, Zhe Liu, Siqi Sun

Learning Optimal Interventions
Jonas Mueller, David Reshef, George Du, Tommi Jaakkola

Learning Structured Weight Uncertainty in Bayesian Neural Networks
Shengyang Sun, Changyou Chen, Lawrence Carin

Learning the Network Structure of Heterogeneous Data via Pairwise Exponential Markov Random Fields
Youngsuk Park, David Hallac, Stephen Boyd, Jure Leskovec

Learning Theory for Conditional Risk Minimization
Alexander Zimin, Christoph Lampert

Learning Time Series Detection Models from Temporally Imprecise Labels
Roy Adams, Ben Marlin

Learning with feature feedback: from theory to practice
Stefanos Poulis, Sanjoy Dasgupta

Least-Squares Log-Density Gradient Clustering for Riemannian Manifolds
Mina Ashizawa, Hiroaki Sasaki, Tomoya Sakai, Masashi Sugiyama

Less than a Single Pass: Stochastically Controlled Stochastic Gradient Method
Lihua Lei, Michael Jordan

Linear Convergence of Stochastic Frank Wolfe Variants
Chaoxu Zhou, Donald Goldfarb, Garud Iyengar

Linear Thompson Sampling Revisited
Marc Abeille, Alessandro Lazric

Lipschitz Density-Ratios, Structured Data, and Data-driven Tuning
Samory Kpotufe

Local Group Invariant Representations via Orbit Embeddings
Anant Raj, Abhishek Kumar, Youssef Mroueh, Tom Fletcher, Bernhard Schoelkopf

Local Perturb-and-MAP for Structured Prediction
Gedas Bertasius, Lorenzo Torresani, Jianbo Shi, Qiang Liu

Localized Lasso for High-Dimensional Regression
Makoto Yamada, Takeuchi Koh, Tomoharu Iwata, John Shawe-Taylor, Samuel Kaski

Lower Bounds on Active Learning for Graphical Model Selection
Jonathan Scarlett, Volkan Cevher

Markov Chain Truncation for Doubly-Intractable Inference
Colin Wei, Iain Murray

Minimax Approach to Variable Fidelity Data Interpolation
Alexey Zaytsev, Evgeny Burnaev

Minimax density estimation for growing dimension
Daniel McDonald

Minimax Gaussian Classification & Clustering
Tianyang Li, Xinyang Yi, Constantine Carmanis, Pradeep Ravikumar

Minimax-optimal semi-supervised regression on unknown manifolds
Amit Moscovich, Ariel Jaffe, Boaz Nadler

Modal-set estimation with an application to clustering
Heinrich Jiang, Samory Kpotufe

Near-optimal Bayesian Active Learning with Correlated and Noisy Tests
Yuxin Chen, Hamed Hassani, Andreas Krause

Nearly Instance Optimal Sample Complexity Bounds for Top-k Arm Selection
Lijie Chen, Jian Li, Mingda Qiao

Non-Count Symmetries in Boolean & Multi-Valued Probabilistic Graphical Models
Parag Singla, Ritesh Noothigattu, Ankit Anand, Mausam

Non-square matrix sensing without spurious local minima via the Burer-Monteiro approach
Dohyung Park, Anastasios Kyrillidis, Constantine Carmanis, Sujay Sanghavi

Nonlinear ICA of Temporally Dependent Stationary Sources
Aapo Hyvarinen, Hiroshi Morioka

On the Hyperprior Choice for the Global Shrinkage Parameter in the Horseshoe Prior
Juho Piironen, Aki Vehtari

On the Interpretability of Conditional Probability Estimates in the Agnostic Setting
Yihan Gao, Aditya Parameswaran, Jian Peng

On the learnability of fully-connected neural networks
Yuchen Zhang, Jason Lee, Martin Wainwright, Michael Jordan

On the Troll-Trust Model for Edge Sign Prediction in Social Networks
Géraud Le Falher, Nicolo Cesa-Bianchi, Claudio Gentile, Fabio Vitale

Online Learning with Partial Monitoring: Optimal Convergence Rates
Joon Kwon, Vianney Perchet

Online Nonnegative Matrix Factorization with General Divergences
Renbo Zhao, Vincent Tan, Huan Xu

Online Optimization of Smoothed Piecewise Constant Functions
Vincent Cohen-Addad, Varun Kanade

Optimal Recovery of Tensor Slices
Andrew Li, Vivek Farias

Optimistic Planning for the Stochastic Knapsack Problem
Ciara Pike-Burke, Steffen Grunewalder

Orthogonal Tensor Decompositions via Two-Mode Higher-Order SVD (HOSVD)
Miaoyan Wang, Yun Song

Performance Bounds for Graphical Record Linkage
Rebecca C. Steorts, Mattew Barnes, Willie Neiswanger

Phase Retrieval Meets Statistical Learning Theory: A Flexible Convex Relaxation
Sohail Bahmani, Justin Romberg

Poisson intensity estimation with reproducing kernels
Seth Flaxman, Yee Whye Teh, Dino Sejdinovic

Prediction Performance After Learning in Gaussian Process Regression
Johan Wagberg, Dave Zachariah, Thomas Schon, Petre Stoica

Quantifying the accuracy of approximate diffusions and Markov chains
Jonathan Huggins, James Zou

Random Consensus Robust PCA
Daniel Pimentel-Alarcon, Robert Nowak

Random projection design for scalable implicit smoothing of randomly observed stochastic processes
Francois Belletti, Evan Sparks, Alexandre Bayen, Kurt Keutzer, Joseph Gonzalez

Rank Aggregation and Prediction with Item Features
Kai-Yang Chiang, Cho-Jui Hsieh, Inderjit Dhillon

Rapid Mixing Swendsen-Wang Sampler for Stochastic Partitioned Attractive Models
Sejun Park, Yunhun Jang, Andreas Galanis, Jinwoo Shin, Daniel Stefankovic, Eric Vigoda

Recurrent Switching Linear Dynamical Systems
Scott Linderman, Andrew Miller, David Blei, Ryan Adams, Liam Paninski, Matthew Johnson

Regression Uncertainty on the Grassmannian
Yi Hong, Xiao Yang, Roland Kwitt, Martin Styner, Marc Niethammer

Regret Bounds for Lifelong Learning
Pierre Alquier, Tien Mai, Massimiliano Pontil

Regret Bounds for Transfer Learning in Bayesian Optimisation
Alistair Shilton, Sunil Gupta, Santu Rana, Svetha Venkatesh

Rejection Sampling Variational Inference
Christian Naesseth, Francisco Ruiz, Scott Linderman, David Blei

Relativistic Monte Carlo
Xiaoyu Lu, Valerio Perrone, Leonard Hasenclever, Yee Whye Teh, Sebastian Vollmer

Removing Phase Transitions from Gibbs Measures
Ian Fellows

Robust and Efficient Computation of Eigenvectors in a Generalized Spectral Method for Constrained Clustering
Chengming Jiang, Huiqing Xie, Zhaojun Bai

Robust Causal Estimation in the Large-Sample Limit without Strict Faithfulness
Ioan Gabriel Bucur, Tom Heskes, Tom Claassen

Scalable Convex Multiple Sequence Alignment via Entropy-Regularized Dual Decomposition
Jiong Zhang, Ian En-Hsu Yen, Pradeep Ravikumar, Inderjit Dhillon

Scalable Greedy Support Selection via Weak Submodularity
Rajiv Khanna, Ethan Elenberg, Joydeep Ghosh, Alex Dimakis

Scalable Learning of Non-Decomposable Objectives
Elad Eban, Mariano Schain, Alan Mackey, Ariel Gordon, Ryan Rifkin, Gal Elidan

Scalable variational inference for super resolution microscopy
Ruoxi Sun, Evan Archer, Liam Paninski

Scaling Submodular Maximization via Pruned Submodularity Graphs
Tianyi Zhou, Hua Ouyang, Yi Chang, Jeff Blimes, Carlos Guestrin

Sequential Graph Matching with Sequential Monte Carlo
Seong-Hwan Jun, Alexandre Bouchard-Cote, Samuel W.K. Wong

Sequential Multiple Hypothesis Testing with Type I Error Control
Alan Malek, Yinlam Chow, Mohammad Ghavamzadeh, Sumeet Katariya

Signal-based Bayesian Seismic Monitoring
David Moore, Stuart Russell

Sketching Meets Random Projection in the Dual: A Provable Recovery Algorithm for Big and High-dimensional Data
Jialei Wang, Jason Lee, Mehrdad Mahdavi, Mladen Kolar, Nati Srebro

Sketchy Decisions: Convex Low-Rank Matrix Optimization with Optimal Storage
Alp Yurtsever, Madeleine Udell, Joel Tropp, Volkan Cevher

Sparse Accelerated Exponential Weights
Pierre Gaillard, Olivier Wintenberger

Sparse Randomized Partition Trees for Nearest Neighbor Search
Kaushik Sinha, Omid Keivani

Spatial Decompositions for Large Scale SVMs
Philipp Thomann, Ingo Steinwart, Ingrid Blaschzyk, Mona Meister

Spectral Methods for Correlated Topic Models
Forough Arabshahi, Anima Anandkumar

Stochastic Difference of Convex Algorithm and its Application to Training Deep Boltzmann Machines
Atsushi Nitanda, Taiji Suzuki

Stochastic Rank-1 Bandits
Sumeet Katariya, Branislav Kveton, Csaba Szepesvari, Claire Vernade, Zheng Wen

Structured adaptive and random spinners for fast machine learning computations
Mariusz Bojarski, Anna Choromanska, Krzysztof Choromanski, Francois Fagan, Cedric Gouy-Pailler, Anne Morvan, Nourhan Sakr, Tamas Sarlos, Jamal Atif

Tensor-Dictionary Learning with Deep Kruskal-Factor Analysis
Andrew Stevens, Yunchen Pu, Yannan Sun, Gregory Spell, Lawrence Carin

The End of Optimism? An Asymptotic Analysis of Finite-Armed Linear Bandits
Tor Lattimore, Csaba Szepesvari

Thompson Sampling for Linear-Quadratic Control Problems
Marc Abeille, Alessandro Lazric

Tracking Objects with Higher Order Interactions via Delayed Column Generation
Shaofei Wang, Steffen Wolf, Charless Fowlkes, Julian Yarkony

Trading off Rewards and Errors in Multi-Armed Bandits
Akram Erraqabi, Alessandro Lazric, Michal Valko, Yun-En Liu, Emma Brunskill

Training Fair Classifiers
Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez Rogriguez, Krishna Gummadi

Unsupervised Sequential Sensor Acquisition
Manjesh Hanawal, Venkatesh Saligrama, Csaba Szepesvari

Value-Aware Loss Function for Model-based Reinforcement Learning
Amir-Massoud Farahmand, Andre Barreto, Daniel Nikovski


Reviewer Instructions for AISTATS 2017

Reviews must be entered electronically through the CMT system for AISTATS 2017.

Review Content

Each review should begin with a paragraph providing an overview of the paper, and summarizing its main contributions. In particular, some thought should be given to how the paper fits with the aims and topics of the conference (not interpreted overly narrowly). The paragraph should relate the ideas in the paper to to previous work in the field.

The next section of the review should deal with major comments, issues that the reviewer sees as standing in the way of acceptance of the paper, or issues that should be addressed prior to publication, or reasons for rejecting the paper.

The final section of the review should deal with any minor issues, such as typographical errors, spelling mistakes, or areas where presentation could be improved.

As was done last year, reviewers may request public or non-proprietary code/data as part of the initial reviews for the purpose of better judging the paper. The authors will then provide the code/data as part of the author response. This might be, for instance, to check whether the authors' methods work as claimed, or whether it correctly treats particular scenarios the authors did not consider in their initial submission. Note this request is NOT to be used to ask the authors to release their code after the paper has been published. Code/data should only be requested in the event that this is the deciding factor in paper acceptance. The request should be reasonable in light of the duration of the discussion period, which limits the time available for review. The SPC member in charge of the paper will confirm whether a code/data request is warranted and reasonable. Authors may only submit separate code and data at the invitation of a reviewer; otherwise, the usual restrictions apply on author response length. The conference chairs will enable the anonymous transfer of code and data to the relevant reviewers.

Evaluation Criteria

Contributions of AISTATS papers can be categorized into four areas a) algorithmic, b) theoretical, c) unifying or d) application.

Algorithmic contributions may make a particular approach feasible for the first time or may extend the applicability of an approach (for example allowing it to be applied to very large data sets).

A theoretical contribution should provide a new result about a model or algorithm. For example convergence proofs, consistency proofs or performance guarantees.

A unifying contribution may bring together several apparently different ideas and show how they are related, providing new insights and directions for future research.

Finally, an application contribution should typically have aspects that present particular statistical challenges which require solution in a novel way or through clever adaptation of existing techniques.

A paper may exhibit one or more of these contributions, where each of them are important in advancing the state of the art in the field. Of course, at AISTATS we are also particularly keen to see work which relates machine learning and statistics or highlights novel connections between the fields or even contrasts them.

One aspect of result presentation that is often neglected is a discussion of the failure cases of an algorithm, often due to concern that reviewers will penalize authors who provide this information. We emphasize that description of failure cases as well as successes should be encouraged and rewarded in submissions.

When reviewing, bear in mind that one of the most important aspects of a successful conference paper is that it should be thought provoking. Thought provoking papers sometimes generate strong reactions on initial reading, which may sometimes be negative. However, if the paper genuinely represents a paradigm shift it may take a little longer than a regular paper to come around to the author's way of thinking. Keep an eye out for such papers, although they may take longer to review, if they do represent an important advance the effort will be well worth it.

Finally, we would like to signal to newcomers to AISTATS (and to machine-learning conferences generally) that the review process is envisioned in exactly the same spirit as in a top quality journal like JRSS B, JASA, or Annals of Statistics. Accepted contributions are published in proceedings, and acceptance is competitive, so authors can rightly include these contributions in their publication list, on par with papers published in top quality journals. Further, AISTATS does not give the option to revise and resubmit: if a paper cannot be accepted with minor revisions (e.g., as proposed by the authors in their response to the reviews), it should be rejected.

Given the culture gap between the statistics and machine learning communities, we thus want to emphasize from the start the required levels of quality and innovation. All deadlines are very strict, as we cannot delay an overall tight schedule.

Confidentiality and Double Blind Process

AISTATS 2017 is a double blind reviewed conference. Whilst we expect authors to remove information that will obviously reveal their identity, we also trust reviewers not to take positive steps to try and uncover the authors' identity.

We are happy for authors to submit material that they have placed online as tech reports (such as in arXiv), or that they have submitted to existing workshops that do not produce published proceedings. This can clearly present a problem with regard to anonymization. Please do not seek out such reports on line in an effort to deanonymize.

The review process is double blind. Authors do not know reviewer identities, and this includes any authors on the senior program committee (i.e., the area chairs). However, area chairs do see reviewer identities. Also, during the discussion phase reviewer identities will be made available to other reviewers. In other words, whilst the authors will not know your identity, your co-reviewers will. This should help facilitate discussion of the papers.

If a reviewer requests code from the authors, this code should be anonymized (e.g., author names should be removed from the file headers). That said, we understand that it might be difficult to remove all traces of the authors from the files, and will exercise reasonable judgment if innocent mistakes are made.

The AISTATS reviewing process is confidential. By agreeing to review you agree not to use ideas, results, code, and data from submitted papers in your work. This includes research and grant proposals. This applies unless that work has appeared in other publicly available formats, for example technical reports or other published work. You also agree not to distribute submitted papers, ideas, code, or data to anyone else. If you request code and accompanying data, you agree that this is provided for your sole use, and only for the purposes of assessing the submission. All code and data must be discarded once the review is complete, and may not be used in further research or transferred to third parties.

The CMT Reviewing System

The first step in the review process is to enter conflicts of interests. These conflicts can be entered as domain names (e.g., cmu.edu) and also by marking specific authors with whom you have a conflict. The use of double blind reviewing means you may not able to determine the papers you have a conflict with, so it is important you go through this list carefully and mark any conflicts. You should mark a conflict with anyone who is or ever was your student or mentor, is a current or recent colleague, or is a close collaborator. If in doubt, it's probably better to mark a conflict, in order to avoid the appearance of impropriety. Your own username should be automatically marked as a conflict, but sometimes the same person may have more than one account, in which case you should definitely mark your other accounts as a conflict as well. If you do not mark a conflict with an author, it is assumed that you do not have a conflict by default.

CMT also requests subject information which will be used to assist allocation of reviewers to papers. Please enter relevant keywords to assist in paper allocation.

You can revise your review multiple times before the submission. Your formal invite to be a reviewer will come from the CMT system. The email address used in this invite is your login, you can change your password with a password reset from the login screen.

Supplementary Material

Supplementary material is allowed by AISTATS 2017. For example, this supplementary material could include proofs, video, source code or audio. As a reviewer you should feel free to make use of this supplementary material to help in your review, though reviewing supplementary material is up to your discretion. One exception is the letter of revision from papers previously submitted to NIPS. If this letter is present in the supplementary material, we ask you to take it into consideration.

Simultaneous Submission

Simultaneous submission to other conference venues in the areas of machine learning and statistics is not permitted.

Simultaneous submission to journal publications of significantly extended versions of the paper is permitted, as long as the publication date of the journal is not before May 2017.