AISTATS 2022

492 papers

Diversity and Generalization in Neural Network Ensembles

Luis A. Ortega, Rafael Cabañas, Andres Masegosa

Outlier-Robust Optimal Transport: Duality, Structure, and Statistical Analysis

Sloan Nietert, Ziv Goldfeld, Rachel Cummings

The Fast Kernel Transform

John P. Ryan, Sebastian E. Ament, Carla P. Gomes, Anil Damle

Equivariant Deep Dynamical Model for Motion Prediction

Bahar Azari, Deniz Erdogmus

Controlling Epidemic Spread using Probabilistic Diffusion Models on Networks

Amy E. Babay, Michael Dinitz, Aravind Srinivasan, Leonidas Tsepenekas, Anil Vullikanti

Statistical and computational thresholds for the planted k-densest sub-hypergraph problem

Luca Corinzia, Paolo Penna, Wojciech Szpankowski, Joachim Buhmann

A Manifold View of Adversarial Risk

Wenjia Zhang, Yikai Zhang, Xiaoling Hu, Mayank Goswami, Chao Chen

Differentially Private Densest Subgraph

Alireza Farhadi, MohammadTaghi Hajiaghayi, Elaine Shi

Learning Tensor Representations for Meta-Learning

Samuel Deng, Yilin Guo, Daniel Hsu, Debmalya Mandal

The role of optimization geometry in single neuron learning

Nicholas Boffi, Stephen Tu, Jean-Jacques Slotine

Adaptive Importance Sampling meets Mirror Descent : a Bias-variance Tradeoff

Anna Korba, François Portier

Online Competitive Influence Maximization

Jinhang Zuo, Xutong Liu, Carlee Joe-Wong, John C. S. Lui, Wei Chen

Transductive Robust Learning Guarantees

Omar Montasser, Steve Hanneke, Nathan Srebro

On Global-view Based Defense via Adversarial Attack and Defense Risk Guaranteed Bounds

Trung Le, Anh Tuan Bui, Le Minh Tri Tue, He Zhao, Paul Montague

Data Appraisal Without Data Sharing

Xinlei Xu, Awni Hannun, Laurens van der Maaten

FLIX: A Simple and Communication-Efficient Alternative to Local Methods in Federated Learning

Elnur Gasanov, Ahmed Khaled, Samuel Horváth, Peter Richtarik

Private Sequential Hypothesis Testing for Statisticians: Privacy, Error Rates, and Sample Size

Wanrong Zhang, Yajun Mei, Rachel Cummings

Feature Collapsing for Gaussian Process Variable Ranking

Isaac Sebenius, Topi Paananen, Aki Vehtari

Can we Generalize and Distribute Private Representation Learning?

Sheikh Shams Azam, Taejin Kim, Seyyedali Hosseinalipour, Carlee Joe-Wong, Saurabh Bagchi

PAC Learning of Quantum Measurement Classes : Sample Complexity Bounds and Universal Consistency

Arun Padakandla, Abram Magner

Polynomial Time Reinforcement Learning in Factored State MDPs with Linear Value Functions

Zihao Deng, Siddartha Devic, Brendan Juba

Entropy Regularized Optimal Transport Independence Criterion

Lang Liu, Soumik Pal, Zaïd Harchaoui

Causal Effect Identification with Context-specific Independence Relations of Control Variables

Ehsan Mokhtarian, Fateme Jamshidi, Jalal Etesami, Negar Kiyavash

Solving Multi-Arm Bandit Using a Few Bits of Communication

Osama A. Hanna, Lin Yang, Christina Fragouli

Sample Complexity of Policy-Based Methods under Off-Policy Sampling and Linear Function Approximation

Zaiwei Chen, Siva Theja Maguluri

Stateful Offline Contextual Policy Evaluation and Learning

Nathan Kallus, Angela Zhou

Robust Training in High Dimensions via Block Coordinate Geometric Median Descent

Anish Acharya, Abolfazl Hashemi, Prateek Jain, Sujay Sanghavi, Inderjit S. Dhillon

Amortised Likelihood-free Inference for Expensive Time-series Simulators with Signatured Ratio Estimation

Joel Dyer, Patrick W. Cannon, Sebastian M. Schmon

Hypergraph Simultaneous Generators

Bahman Pedrood, Carlotta Domeniconi, Kathryn Laskey

Forward Looking Best-Response Multiplicative Weights Update Methods for Bilinear Zero-sum Games

Michail Fasoulakis, Evangelos Markakis, Yannis Pantazis, Constantinos Varsos

Learning from Multiple Noisy Partial Labelers

Peilin Yu, Tiffany Ding, Stephen H. Bach

Predicting the utility of search spaces for black-box optimization: a simple, budget-aware approach

Setareh Ariafar, Justin Gilmer, Zachary Nado, Jasper Snoek, Rodolphe Jenatton

Outcome Assumptions and Duality Theory for Balancing Weights

David A. Bruns-Smith, Avi Feller

Adaptive Sampling for Heterogeneous Rank Aggregation from Noisy Pairwise Comparisons

Yue Wu, Tao Jin, Hao Lou, Pan Xu, Farzad Farnoud

Quadric Hypersurface Intersection for Manifold Learning in Feature Space

Fedor Pavutnitskiy, Sergei O. Ivanov, Evgeniy Abramov, Viacheslav Borovitskiy, Artem Klochkov

Differentiable Bayesian inference of SDE parameters using a pathwise series expansion of Brownian motion

Sanmitra Ghosh, Paul J. Birrell, Daniela De Angelis

On the Implicit Bias of Gradient Descent for Temporal Extrapolation

Edo Cohen-Karlik, Avichai Ben David, Nadav Cohen, Amir Globerson

Rapid Convergence of Informed Importance Tempering

Quan Zhou, Aaron Smith

Two-way Sparse Network Inference for Count Data

Sijia Li, Martı́n López-Garcı́a, Neil D. Lawrence, Luisa Cutillo

Beyond Data Samples: Aligning Differential Networks Estimation with Scientific Knowledge

Arshdeep Sekhon, Zhe Wang, Yanjun Qi

Spectral Robustness for Correlation Clustering Reconstruction in Semi-Adversarial Models

Flavio Chierichetti, Alessandro Panconesi, Giuseppe Re, Luca Trevisan

Adaptive A/B Test on Networks with Cluster Structures

Yang Liu, Yifan Zhou, Ping Li, Feifang Hu

Generalized Group Testing

Xiwei Cheng, Sidharth Jaggi, Qiaoqiao Zhou

Model-agnostic out-of-distribution detection using combined statistical tests

Federico Bergamin, Pierre-Alexandre Mattei, Jakob Drachmann Havtorn, Hugo Sénétaire, Hugo Schmutz

On the Oracle Complexity of Higher-Order Smooth Non-Convex Finite-Sum Optimization

Nicolas Emmenegger, Rasmus Kyng, Ahad N. Zehmakan

Can Functional Transfer Methods Capture Simple Inductive Biases?

Arne Nix, Suhas Shrinivasan, Edgar Y. Walker, Fabian Sinz

Multiple Importance Sampling ELBO and Deep Ensembles of Variational Approximations

Oskar Kviman, Harald Melin, Hazal Koptagel, Victor Elvira, Jens Lagergren

Towards an Understanding of Default Policies in Multitask Policy Optimization

Ted Moskovitz, Michael Arbel, Jack Parker-Holder, Aldo Pacchiano

Non-separable Spatio-temporal Graph Kernels via SPDEs

Alexander V. Nikitin, ST John, Arno Solin, Samuel Kaski

Coresets for Data Discretization and Sine Wave Fitting

Alaa Maalouf, Murad Tukan, Eric Price, Daniel M. Kane, Dan Feldman

Multivariate Quantile Function Forecaster

Kelvin Kan, Francois-Xavier Aubet, Tim Januschowski, Youngsuk Park, Konstantinos Benidis

Tight bounds for minimum ℓ_1-norm interpolation of noisy data

Guillaume Wang, Konstantin Donhauser, Fanny Yang

Increasing the accuracy and resolution of precipitation forecasts using deep generative models

Ilan Price, Stephan Rasp

Testing Granger Non-Causality in Panels with Cross-Sectional Dependencies

Lenon Minorics, Caner Turkmen, David Kernert, Patrick Bloebaum, Laurent Callot

Modeling Conditional Dependencies in Multiagent Trajectories

Yannick Rudolph, Ulf Brefeld

On a Connection Between Fast and Sparse Oblivious Subspace Embeddings

Rui Wang, Wangli Xu

Duel-based Deep Learning system for solving IQ tests

Paulina Tomaszewska, Adam Żychowski, Jacek Mańdziuk

Neural Enhanced Dynamic Message Passing

Fei Gao, Jiang Zhang, Yan Zhang

Provable Continual Learning via Sketched Jacobian Approximations

Reinhard Heckel

Sobolev Norm Learning Rates for Conditional Mean Embeddings

Prem Talwai, Ali Shameli, David Simchi-Levi

Effective Nonlinear Feature Selection Method based on HSIC Lasso and with Variational Inference

Kazuki Koyama, Keisuke Kiritoshi, Tomomi Okawachi, Tomonori Izumitani

Statistical Depth Functions for Ranking Distributions: Definitions, Statistical Learning and Applications

Morgane Goibert, Stéphan Clémençon, Ekhine Irurozki, Pavlo Mozharovskyi

Towards Understanding Biased Client Selection in Federated Learning

Yae Jee Cho, Jianyu Wang, Gauri Joshi

Data-splitting improves statistical performance in overparameterized regimes

Nicole Muecke, Enrico Reiss, Jonas Rungenhagen, Markus Klein

Minimal Expected Regret in Linear Quadratic Control

Yassir Jedra, Alexandre Proutiere

REPID: Regional Effect Plots with implicit Interaction Detection

Julia Herbinger, Bernd Bischl, Giuseppe Casalicchio

Solving Marginal MAP Exactly by Probabilistic Circuit Transformations

YooJung Choi, Tal Friedman, Guy Van den Broeck

Triangular Flows for Generative Modeling: Statistical Consistency, Smoothness Classes, and Fast Rates

Nicholas J. Irons, meyer scetbon, Soumik Pal, Zaïd Harchaoui

Efficient computation of the the volume of a polytope in high-dimensions using Piecewise Deterministic Markov Processes

Augustin Chevallier, Frederic Cazals, Paul Fearnhead

Differentially Private Federated Learning on Heterogeneous Data

Maxence Noble, Aurélien Bellet, Aymeric Dieuleveut

A Non-asymptotic Approach to Best-Arm Identification for Gaussian Bandits

Antoine Barrier, Aurélien Garivier, Tomáš Kocák

The Importance of Future Information in Credit Card Fraud Detection

Van Bach Nguyen, Kanishka Ghosh Dastidar, Michael Granitzer, Wissam Siblini

Finite Sample Analysis of Mean-Volatility Actor-Critic for Risk-Averse Reinforcement Learning

Khaled Eldowa, Lorenzo Bisi, Marcello Restelli

Pick-and-Mix Information Operators for Probabilistic ODE Solvers

Nathanael Bosch, Filip Tronarp, Philipp Hennig

Compressed Rule Ensemble Learning

Malte Nalenz, Thomas Augustin

Efficient and passive learning of networked dynamical systems driven by non-white exogenous inputs

Harish Doddi, Deepjyoti Deka, Saurav Talukdar, Murti Salapaka

Learning Pareto-Efficient Decisions with Confidence

Sofia Ek, Dave Zachariah, Peter Stoica

On Some Fast And Robust Classifiers For High Dimension, Low Sample Size Data

Sarbojit Roy, Jyotishka Ray Choudhury, Subhajit Dutta

Provable Adversarial Robustness for Fractional Lp Threat Models

Alexander J. Levine, Soheil Feizi

GraphAdaMix: Enhancing Node Representations with Graph Adaptive Mixtures

Da Sun Handason Tam, Siyue Xie, Wing Cheong Lau

Mean Nyström Embeddings for Adaptive Compressive Learning

Antoine Chatalic, Luigi Carratino, Ernesto De Vito, Lorenzo Rosasco

Sobolev Transport: A Scalable Metric for Probability Measures with Graph Metrics

Tam Le, Truyen Nguyen, Dinh Phung, Viet Anh Nguyen

An Unsupervised Hunt for Gravitational Lenses

Stephen Sheng, Keerthi Vasan G C, Chi Po P Choi, James Sharpnack, Tucker Jones

On the Convergence of Stochastic Extragradient for Bilinear Games using Restarted Iteration Averaging

Chris Junchi Li, Yaodong Yu, Nicolas Loizou, Gauthier Gidel, Yi Ma

Marginalising over Stationary Kernels with Bayesian Quadrature

Saad Hamid, Sebastian Schulze, Michael A. Osborne, Stephen Roberts

Information-Theoretic Analysis of Epistemic Uncertainty in Bayesian Meta-learning

Sharu Theresa Jose, Sangwoo Park, Osvaldo Simeone

Convex Analysis of the Mean Field Langevin Dynamics

Atsushi Nitanda, Denny Wu, Taiji Suzuki

Primal-Dual Stochastic Mirror Descent for MDPs

Daniil Tiapkin, Alexander Gasnikov

Laplacian Constrained Precision Matrix Estimation: Existence and High Dimensional Consistency

Eduardo Pavez

Exact Community Recovery over Signed Graphs

Xiaolu Wang, Peng Wang, Anthony Man-Cho So

A cautionary tale on fitting decision trees to data from additive models: generalization lower bounds

Yan Shuo Tan, Abhineet Agarwal, Bin Yu

Towards Agnostic Feature-based Dynamic Pricing: Linear Policies vs Linear Valuation with Unknown Noise

Jianyu Xu, Yu-Xiang Wang

LocoProp: Enhancing BackProp via Local Loss Optimization

Ehsan Amid, Rohan Anil, Manfred Warmuth

On Coresets for Fair Regression and Individually Fair Clustering

Rachit Chhaya, Anirban Dasgupta, Jayesh Choudhari, Supratim Shit

Sample Complexity of Robust Reinforcement Learning with a Generative Model

Kishan Panaganti, Dileep Kalathil

Disentangling Whether from When in a Neural Mixture Cure Model for Failure Time Data

Matthew Engelhard, Ricardo Henao

Learning Interpretable, Tree-Based Projection Mappings for Nonlinear Embeddings

Arman S. Zharmagambetov, Miguel Á. Carreira-Perpiñán

Expressivity of Neural Networks via Chaotic Itineraries beyond Sharkovsky’s Theorem

Clayton H. Sanford, Vaggos Chatziafratis

Learning and Generalization in Overparameterized Normalizing Flows

Kulin Shah, Amit Deshpande, Navin Goyal

Learning Sparse Fixed-Structure Gaussian Bayesian Networks

Arnab Bhattacharyya, Davin Choo, Rishikesh Gajjala, Sutanu Gayen, Yuhao Wang