Selected Publications by Topic


For a more complete list, see my Google Scholar profile or my CV

Navigation of topics: Survey/Tutorial — Group Testing — Black-Box Optimization — Bandit Algorithms — Generative Priors — Sparse Recovery — Graphical Models — Multi-Hop Codes — Miscellaneous — Mismatched Decoding in Information Theory — Refined Asymptotics in Information Theory

Survey/Tutorial

Group Testing: An Information Theory Perspective
Matthew Aldridge, Oliver Johnson, and Jonathan Scarlett
Foundations and Trends in Communications and Information Theory, Volume 15, Issue 3-4, pp. 196-392, Dec. 2019
[publisher] [arxiv]
Information-Theoretic Foundations of Mismatched Decoding
Jonathan Scarlett, Albert Guillén i Fàbregas, Anelia Somekh-Baruch, and Alfonso Martinez
Foundations and Trends in Communications and Information Theory, Volume 17, Issue 2-3, pp. 149-400, Aug. 2020
[publisher] [arxiv]
Theoretical Perspectives on Deep Learning Methods in Inverse Problems
Jonathan Scarlett, Reinhard Heckel, Miguel R. D. Rodrigues, Paul Hand, and Yonina C. Eldar
IEEE Journal on Selected Areas in Information Theory, Volume 3, Issue 3, pp. 433-453, Sept. 2022
[ieee] [arxiv]
An Introductory Guide to Fano's Inequality with Applications in Statistical Estimation
Jonathan Scarlett and Volkan Cevher
Book chapter in Information-Theoretic Methods in Data Science (Rodrigues/Eldar), Cambridge University Press, 2021
[publisher] [arxiv]

Group Testing

Exact Thresholds for Noisy Non-Adaptive Group Testing
Junren Chen and Jonathan Scarlett
Accepted to ACM-SIAM Symposium on Discrete Algorithms (SODA)
[arxiv]
Approximate Message Passing with Rigorous Guarantees for Pooled Data and Quantitative Group Testing
Nelvin Tan, Pablo Pascual Cobo, Jonathan Scarlett, and Ramji Venkataramanan
SIAM Journal on Mathematics of Data Science (SIMODS), Volume 6, Issue 4, pp. 1027-1054, 2024
[arxiv]
Concomitant Group Testing
Thach V. Bui and Jonathan Scarlett
IEEE Transactions on Information Theory, Volume 70, Issue 10, pp. 7179-7192, Oct. 2024
[ieee] [arxiv]
Fast Splitting Algorithms for Sparsity-Constrained and Noisy Group Testing
Eric Price, Jonathan Scarlett, and Nelvin Tan
Information and Inference: A Journal of the IMA, Volume 12, Issue 2, pp. 1141-1171, June 2023
[ima] [arxiv]
Performance Bounds for Group Testing With Doubly-Regular Designs
Nelvin Tan, Way Tan, and Jonathan Scarlett
IEEE Transactions on Information Theory, Volume 69, Issue 2, pp. 1224-1243, Feb. 2023
[ieee] [arxiv]
Model-Based and Graph-Based Priors for Group Testing
Ivan Lau, Jonathan Scarlett, and Sun Yang
IEEE Transaction on Signal Processing, Volume 70, pp. 6035-6050, Dec. 2022
[ieee] [arxiv]
Optimal Non-Adaptive Probabilistic Group Testing in General Sparsity Regimes
Wei Heng Bay, Eric Price, and Jonathan Scarlett
Information and Inference: A Journal of the IMA, Volume 11, Issue 3, pp. 1037-1053, Sept. 2022
[ima] [arxiv]
Near-Optimal Sparsity-Constrained Group Testing: Improved Bounds and Algorithms
Oliver Gebhard, Max Hahn-Klimroth, Olaf Parczyk, Manuel Penschuck, Maurice Rolvien, Jonathan Scarlett, and Nelvin Tan
IEEE Transactions on Information Theory, Volume 68, Issue 5, pp. 3253-3280, May 2022
[ieee] [arxiv]
Noisy Adaptive Group Testing via Noisy Binary Search
Bernard Teo and Jonathan Scarlett
IEEE Transactions on Information Theory, Volume 68, Issue 5, pp. 3340-3353, May 2022
[ieee] [arxiv]
Sublinear-Time Non-Adaptive Group Testing with O(k log n) Tests via Bit-Mixing Coding
Steffen Bondorf, Binbin Chen, Jonathan Scarlett, Haifeng Yu, and Yuda Zhao
IEEE Transactions on Information Theory, Volume 67, Issue 3, pp. 1559-1570, March 2021
[ieee] [arxiv]
On the All-Or-Nothing Behavior of Bernoulli Group Testing
Lan V. Truong, Matthew Aldridge, and Jonathan Scarlett
IEEE Journal on Selected Areas in Information Theory (Special Issue on Estimation and Inference), Volume 1, Issue 3, pp. 669-680, Nov. 2020
[ieee] [arxiv]
A Fast Binary Splitting Approach to Non-Adaptive Group Testing
Eric Price and Jonathan Scarlett
International Conference on Randomization and Computation (RANDOM), 2020
[drops] [arxiv]
Noisy Non-Adaptive Group Testing: A (Near-)Definite Defectives Approach
Jonathan Scarlett and Oliver Johnson
IEEE Transactions on Information Theory, Volume 66, Issue 6, pp. 3775-3797, June 2020
[ieee] [arxiv]
A MaxSAT-Based Framework for Group Testing
Bishwamittra Ghosh, Lorenzo Ciampiconi, Jonathan Scarlett, and Kuldeep S. Meel
AAAI Conference on Artificial Intelligence, 2020
[aaai] [github]
Noisy Adaptive Group Testing: Bounds and Algorithms
Jonathan Scarlett
IEEE Transactions on Information Theory, Volume 65, Issue 6, pp. 3646-3661, June 2019
[ieee] [arxiv]
Performance of Group Testing Algorithms with Near-Constant Tests-Per-Item
Oliver Johnson, Matthew Aldridge, and Jonathan Scarlett
IEEE Transactions on Information Theory, Volume 65, Issue 2, pp. 707-723, Feb. 2019
[ieee] [arxiv]
Near-Optimal Noisy Group Testing via Separate Decoding of Items
Jonathan Scarlett and Volkan Cevher
IEEE Journal on Selected Topics in Signal Processing (Special Issue on Information-Theoretic Methods in Data Acquisition, Analysis, and Processing), Volume 12, Issue 5, pp. 902-915, Oct. 2018
[ieee] [arxiv]
Phase Transitions in Group Testing
Jonathan Scarlett and Volkan Cevher
ACM-SIAM Symposium on Discrete Algorithms (SODA), 2016
[acm] [epfl]

Black-Box Optimization

Regret Bounds for Noise-Free Cascaded Kernelized Bandits
Zihan Li and Jonathan Scarlett
Transactions on Machine Learning Research (TMLR), May 2024
[openreview] [arxiv]
No-Regret Algorithms for Safe Bayesian Optimization with Monotonicity Constraints
Arpan Losalka and Jonathan Scarlett
International Conference on Artificial Intelligence and Statistics (AISTATS), 2024
[pmlr] [arxiv]
Benefits of Monotonicity in Safe Exploration with Gaussian Processes
Arpan Losalka and Jonathan Scarlett
Conference on Uncertainty in Artificial Intelligence (UAI), 2023
[pmlr] [arxiv]
A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Bandits
Ilija Bogunovic, Zihan Li, Andreas Krause, and Jonathan Scarlett
Conference on Neural Information Processing Systems (NeurIPS), 2022
[neurips] [arxiv]
Adversarial Attacks on Gaussian Process Bandits
Eric Han and Jonathan Scarlett
International Conference on Machine Learning (ICML), 2022
[pmlr] [arxiv]
Improved Convergence Rates for Sparse Approximation Methods in Kernel-Based Learning
Sattar Vakili, Jonathan Scarlett, Da-shan Shiu, and Alberto Bernacchia
International Conference on Machine Learning (ICML), 2022
[pmlr] [arxiv]
Gaussian Process Bandit Optimization with Few Batches
Zihan Li and Jonathan Scarlett
International Conference on Artificial Intelligence and Statistics (AISTATS), 2022
[pmlr] [arxiv]
Tight Regret Bounds for Noisy Optimization of a Brownian Motion
Zexin Wang, Vincent Y. F. Tan, and Jonathan Scarlett
IEEE Transactions on Signal Processing, Volume 70, pp. 1072-1087, Jan. 2022
[ieee] [arxiv]
On Lower Bounds for Standard and Robust Gaussian Process Bandit Optimization
Xu Cai and Jonathan Scarlett
International Conference on Machine Learning (ICML), 2021
[pmlr] [arxiv]
Lenient Regret and Good-Action Identification in Gaussian Process Bandits
Xu Cai, Selwyn Gomes, and Jonathan Scarlett
International Conference on Machine Learning (ICML), 2021
[pmlr] [arxiv]
High-Dimensional Bayesian Optimization via Tree-Structured Graphical Models
Eric Han, Ishank Arora, and Jonathan Scarlett
AAAI Conference on Artificial Intelligence, 2021
[aaai] [arxiv]
Corruption-Tolerant Gaussian Process Bandit Optimization
Ilija Bogunovic, Andreas Krause, and Jonathan Scarlett
International Conference on Artificial Intelligence and Statistics (AISTATS), 2020
[pmlr] [arxiv]
Adversarially Robust Optimization with Gaussian Processes
Ilija Bogunovic, Jonathan Scarlett, Stefanie Jegelka, and Volkan Cevher
Conference on Neural Information Processing Systems (NeurIPS), 2018
[neurips] [arxiv]
Tight Regret Bounds for Bayesian Optimization in One Dimension
Jonathan Scarlett
International Conference on Machine Learning (ICML), 2018
[pmlr] [arxiv]
High-Dimensional Bayesian Optimization via Additive Models with Overlapping Groups
Paul Rolland, Jonathan Scarlett, Ilija Bogunovic, and Volkan Cevher
International Conference on Artificial Intelligence and Statistics (AISTATS), 2018
[pmlr] [arxiv]
Lower Bounds on Regret for Noisy Gaussian Process Bandit Optimization
Jonathan Scarlett, Ilija Bogunovic, and Volkan Cevher
Conference on Learning Theory (COLT), 2017
[pmlr] [arxiv]
Truncated Variance Reduction: A Unified Approach to Bayesian Optimization and Level-Set Estimation
Ilija Bogunovic, Jonathan Scarlett, Andreas Krause, and Volkan Cevher
Conference on Neural Information Processing Systems (NeurIPS), 2016
[neurips] [arxiv]
Time-Varying Gaussian Process Bandit Optimization
Ilija Bogunovic, Jonathan Scarlett, and Volkan Cevher
International Conference on Artificial Intelligence and Statistics (AISTATS), 2016
[pmlr] [arxiv]

Bandit Algorithms

A General Framework for Clustering and Distribution Matching with Bandit Feedback
Recep Can Yavas, Yuqi Huang, Vincent Y. F. Tan, and Jonathan Scarlett
In submission (Preprint)
[arxiv]
Communication-Constrained Bandits under Additive Gaussian Noise
Prathamesh Mayekar, Jonathan Scarlett, and Vincent Y.F. Tan
International Conference on Machine Learning (ICML), 2023
[pmlr] [arxiv]
Max-Quantile Grouped Infinite-Arm Bandits
Ivan Lau, Yan Hao Ling, Mayank Shrivastava, and Jonathan Scarlett
International Conference on Algorithmic Learning Theory (ALT), 2023
[pmlr] [arxiv]
Max-Min Grouped Bandits
Zhenlin Wang and Jonathan Scarlett
AAAI Conference on Artificial Intelligence, 2022
[aaai] [arxiv]
Stochastic Linear Bandits Robust to Adversarial Attacks
Ilija Bogunovic, Arpan Losalka, Andreas Krause, and Jonathan Scarlett
International Conference on Artificial Intelligence and Statistics (AISTATS), 2021
[pmlr] [arxiv]

Generative Priors

A Unified Framework for Uniform Signal Recovery in Nonlinear Generative Compressed Sensing
Junren Chen, Jonathan Scarlett, Michael Ng, and Zhaoqiang Liu
Conference on Neural Information Processing Systems (NeurIPS), 2023
[neurips] [arxiv]
Generative Principal Component Analysis
Zhaoqiang Liu, Jiulong Liu, Subhroshekhar Ghosh, Jun Han, and Jonathan Scarlett
International Conference on Learning Representations (ICLR), 2022
[openreview] [arxiv]
Towards Sample-Optimal Compressive Phase Retrieval with Sparse and Generative Priors
Zhaoqiang Liu, Subhroshekhar Ghosh, and Jonathan Scarlett
Conference on Neural Information Processing Systems (NeurIPS), 2021
[neurips] [arxiv]
The Generalized Lasso with Nonlinear Observations and Generative Priors
Zhaoqiang Liu and Jonathan Scarlett
Conference on Neural Information Processing Systems (NeurIPS), 2020
[neurips] [arxiv]
Sample Complexity Bounds for 1-bit Compressive Sensing and Binary Stable Embeddings with Generative Priors
Zhaoqiang Liu, Selwyn Gomes, Avtansh Tiwari, and Jonathan Scarlett
International Conference on Machine Learning (ICML), 2020
[icml] [arxiv]
Information-Theoretic Lower Bounds for Compressive Sensing with Generative Models
Zhaoqiang Liu and Jonathan Scarlett
IEEE Journal on Selected Areas in Information Theory (Special Issue on Deep Learning), Volume 1, Issue 1, pp. 292-303, May 2020
[ieee] [arxiv]

Sparse Recovery

Robust Instance Optimal Phase-Only Compressed Sensing
Junren Chen, Zhaoqiang Liu, Michael K. Ng, and Jonathan Scarlett
In submission (Preprint)
[arxiv]
Support Recovery in the Phase Retrieval Model: Information-Theoretic Fundamental Limits
Lan V. Truong and Jonathan Scarlett
IEEE Transactions on Information Theory, Volume 66, Issue 12, pp. 7887-7910, Dec. 2020
[ieee] [arxiv]
An Adaptive Sublinear-Time Block Sparse Fourier Transform
Volkan Cevher, Michael Kapralov, Jonathan Scarlett, and Amir Zandieh
ACM Symposium on Theory of Computing (STOC), 2017
[acm] [arxiv]
Limits on Support Recovery with Probabilistic Models: An Information-Theoretic Framework
Jonathan Scarlett and Volkan Cevher
IEEE Transactions on Information Theory, Volume 63, Issue 1, pp. 593-620, Jan. 2017
[ieee] [arxiv]
Learning-Based Compressive Subsampling
Luca Baldassarre, Yen-Huan Li, Jonathan Scarlett, Baran Gözcü, Ilija Bogunovic, and Volkan Cevher
IEEE Journal on Selected Topics in Signal Processing (Special Issue on Structured Matrices in Signal and Data Processing), Volume 10, Issue 4, pp. 809-822, March 2016
[ieee] [arxiv]
Sparsistency of l1-Regularized M-estimators
Yen-Huan Li, Jonathan Scarlett, Pradeep Ravikumar, and Volkan Cevher
International Conference on Artificial Intelligence and Statistics (AISTATS), 2015
[pmlr] [arxiv]
Compressed Sensing with Prior Information: Information-Theoretic Limits and Practical Decoders
Jonathan Scarlett, Jamie Evans, and Subhrakanti Dey
IEEE Transactions on Signal Processing, Volume 61, Issue 2, pp. 427-439, Jan. 2013
[ieee]

Graphical Models

Learning Gaussian Graphical Models via Multiplicative Weights
Anamay Chaturvedi and Jonathan Scarlett
International Conference on Artificial Intelligence and Statistics (AISTATS), 2020
[pmlr] [arxiv]
Learning Erdős-Rényi Random Graphs via Edge Detecting Queries
Zihan Li, Matthias Fresacher, and Jonathan Scarlett
Conference on Neural Information Processing Systems (NeurIPS), 2019
[neurips] [arxiv]
Lower Bounds on Active Learning for Graphical Model Selection
Jonathan Scarlett and Volkan Cevher
International Conference on Artificial Intelligence and Statistics (AISTATS), 2017
[pmlr] [arxiv]
On the Difficulty of Selecting Ising Models with Approximate Recovery
Jonathan Scarlett and Volkan Cevher
IEEE Transactions on Signal and Information Processing over Networks (Special Issue on Inference and Learning over Networks), Volume 2, Issue 4, pp. 625-638, July 2016
[ieee] [arxiv]

Multi-Hop Codes

Optimal 1-bit Error Exponent for 2-hop Relaying with Binary-Input Channels
Yan Hao Ling and Jonathan Scarlett
IEEE Transactions on Information Theory, Volume 70, Issue 11, pp. 7599-7615, Nov. 2024
[ieee] [arxiv]
Maxflow-Based Bounds for Low-Rate Information Propagation over Noisy Networks
Yan Hao Ling and Jonathan Scarlett
IEEE Transactions on Information Theory, Volume 70, Issue 6, pp. 3840-3854, June 2024
[ieee] [arxiv]
Multi-Bit Relaying over a Tandem of Channels
Yan Hao Ling and Jonathan Scarlett
IEEE Transactions on Information Theory, Volume 69, Issue 6, pp. 3511-3524, June 2023
[ieee] [arxiv]
Simple Coding Techniques for Many-Hop Relaying
Yan Hao Ling and Jonathan Scarlett
IEEE Transactions on Information Theory, Volume 68, Issue 11, pp. 7043-7053, Nov. 2022
[ieee] [arxiv]
Optimal Rates of Teaching and Learning Under Uncertainty
Yan Hao Ling and Jonathan Scarlett
IEEE Transactions on Information Theory, Volume 67, Issue 11, pp. 7067-7080, Nov. 2021
[ieee] [arxiv]

Miscellaneous

Kernelized Normalizing Constant Estimation: Bridging Bayesian Quadrature and Bayesian Optimization
Xu Cai and Jonathan Scarlett
AAAI Conference on Artificial Intelligence, 2024
[aaai] [arxiv]
On Average-Case Error Bounds for Kernel-Based Bayesian Quadrature
Xu Cai, Chi Thanh Lam, and Jonathan Scarlett
Transactions on Machine Learning Research (TMLR), July 2023
[openreview] [arxiv]
A Characteristic Function Approach to Deep Implicit Generative Modeling
Abdul Fatir Ansari, Jonathan Scarlett, and Harold Soh
Conference on Computer Vision and Pattern Recognition (CVPR), 2020
[ieee] [arxiv]
Phase Transitions in the Pooled Data Problem
Jonathan Scarlett and Volkan Cevher
Conference on Neural Information Processing Systems (NeurIPS), 2017
[neurips] [arxiv]
Robust Submodular Maximization: A Non-Uniform Partitioning Approach
Ilija Bogunovic, Slobodan Mitrovic, Jonathan Scarlett, and Volkan Cevher
International Conference on Machine Learning (ICML), 2017
[pmlr] [arxiv]

Mismatched Decoding in Information Theory

Mismatched Rate-Distortion Theory: Ensembles, Bounds, and General Alphabets
Millen Kanabar and Jonathan Scarlett
IEEE Transactions on Information Theory, Volume 70, Issue 3, pp. 1525-1539, March 2024
[ieee] [arxiv]
Mismatched Multi-Letter Successive Decoding for the Multiple-Access Channel
Jonathan Scarlett, Alfonso Martinez, and Albert Guillén i Fàbregas
IEEE Transactions on Information Theory, Volume 64, Issue 4, pp. 2253-2266, April 2018
[ieee] [arxiv]
The Dispersion of Nearest-Neighbor Decoding for Additive Non-Gaussian Channels
Jonathan Scarlett, Vincent Y. F. Tan, and Giuseppe Durisi
IEEE Transactions on Information Theory, Volume 63, Issue 1, pp. 81-92, Jan. 2017
[ieee] [arxiv]
Multiuser Random Coding Techniques for Mismatched Decoding
Jonathan Scarlett, Alfonso Martinez, and Albert Guillén i Fàbregas
IEEE Transactions on Information Theory, Volume 62, Issue 7, pp. 3950-3970, July 2016
[ieee] [arxiv]
A Counter-Example to the Mismatched Decoding Converse for Binary-Input Discrete Memoryless Channels
Jonathan Scarlett, Anelia Somekh-Baruch. Alfonso Martinez, and Albert Guillén i Fàbregas
IEEE Transactions on Information Theory, Volume 61, Issue 10, pp. 5387-5395, Oct. 2015
[ieee] [arxiv]
Mismatched Decoding: Error Exponents, Second-Order Rates and Saddlepoint Approximations
Jonathan Scarlett, Alfonso Martinez, and Albert Guillén i Fàbregas
IEEE Transactions on Information Theory, Volume 60, Issue 5, pp. 2647-2666, May 2014
[ieee] [arxiv]

Refined Asymptotics in Information Theory

Exact Error Exponents of Concatenated Codes for DNA Storage
Yan Hao Ling and Jonathan Scarlett
In submission (Preprint)
[arxiv]
Generalized Random Gilbert-Varshamov Codes
Anelia Somekh-Baruch, Jonathan Scarlett, and Albert Guillén i Fàbregas
IEEE Transactions on Information Theory, Volume 65, Issue 6, pp. 3452-3469, June 2019
[ieee] [arxiv]
Second-Order Asymptotics for the Gaussian MAC with Degraded Message Sets
Jonathan Scarlett and Vincent Y. F. Tan
IEEE Transactions on Information Theory, Volume 61, Issue 12, pp. 6700-6718, Dec. 2015
[ieee] [arxiv]
On the Dispersions of the Gel'fand-Pinsker Channel and Dirty Paper Coding
Jonathan Scarlett
IEEE Transactions on Information Theory, Volume 61, Issue 9, pp. 4569-4586, Sept. 2015
[ieee] [arxiv]
Second-Order Rate Region of Constant-Composition Codes for the Multiple-Access Channel
Jonathan Scarlett, Alfonso Martinez, and Albert Guillén i Fàbregas
IEEE Transactions on Information Theory, Volume 61, Issue 1, pp. 157-172, Jan. 2015
[ieee] [arxiv]
Expurgated Random-Coding Ensembles: Exponents, Refinements and Connections
Jonathan Scarlett, Li Peng, Neri Merhav, Alfonso Martinez, and Albert Guillén i Fàbregas
IEEE Transactions on Information Theory, Volume 60, Issue 8, pp. 4449-4462, Aug. 2014
[ieee] [arxiv]
[Back to top]