Jonathan Scarlett

 

 

Research interests:

  • Information theory
  • Machine learning
  • High-dimensional statistics
  • Signal processing 


 

I have moved to the National University of Singapore (Department of Computer Science & Department of Mathematics).  My new home page is http://www.comp.nus.edu.sg/~scarlett/

 

 

PUBLICATIONS

J. Scarlett : An Introductory Guide to Fano's Inequality with Applications in Statistical Estimation; Information-Theoretic Methods in Data Science; Cambridge University Press, 2019-06-12.
J. Scarlett; I. Bogunovic; V. Cevher : Overlapping Multi-Bandit Best Arm Identification. 2019. The 2019 IEEE International Symposium on Information Theory (ISIT), Paris, France, July 7-12, 2019.
J. Scarlett; V. Cevher : Near-Optimal Noisy Group Testing via Separate Decoding of Items; IEEE Journal of Selected Topics In Signal Processing. 2018-10-01. DOI : 10.1109/JSTSP.2018.2844818.
J. Scarlett; V. Cevher : Near-Optimal Noisy Group Testing via Separate Decoding of Items. 2018-06-17. IEEE International Symposium on Information Theory, Colorado, USA., June 17-22. 2018. p. 2311-2315.
I. Bogunovic; J. Scarlett; S. Jegelka; V. Cevher : Adversarially Robust Optimization with Gaussian Processes. 2018-01-01. 32nd Conference on Neural Information Processing Systems (NIPS), Montreal, CANADA, Dec 02-08, 2018.
I. Bogunovic; J. Scarlett; S. Jegelka; V. Cevher : Adversarially Robust Optimization with Gaussian Processes. 2018. Conference on Neural Information Processing Systems (NIPS), Montreal, 2018.
B. Gözcü; R. Karimi Mahabadi; Y.-H. Li; E. Ilıcak; T. Çukur et al. : Learning-Based Compressive MRI; IEEE Transactions On Medical Imaging. 2018. DOI : 10.1109/TMI.2018.2832540.
P. T. Y. Rolland; J. Scarlett; I. Bogunovic; V. Cevher : High Dimensional Bayesian Optimization via Additive Models with Overlapping Groups. 2018. AISTATS, Lanzarote, Spain, April, 9-11, 2018.
I. Bogunovic; S. Mitrovic; J. Scarlett; V. Cevher : A Distributed Algorithm for Partitioned Robust Submodular Maximization. 2017. IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP).
J. Scarlett; V. Cevher : Phase Transitions in the Pooled Data Problem. 2017. Conference on Neural Information Processing Systems (NIPS), Long Beach, California, December 2017.
J. Scarlett; V. Cevher : Efficient and Near-Optimal Noisy Group Testing: An Information-Theoretic Framework; IEEE Journal of Selected Topics in Signal Processing. 2017.
I. Bogunovic; S. Mitrovic; J. Scarlett; V. Cevher : Robust Submodular Maximization: A Non-Uniform Partitioning Approach. 2017. The 34th International Conference on Machine Learning (ICML), Sydney, 2017.
J. Scarlett; I. Bogunovic; V. Cevher : Lower Bounds on Regret for Noisy Gaussian Process Bandit Optimization. 2017. Conference on Learning Theory (COLT)Conference on Learning Theory (COLT), AmsterdamAmsterdam, Netherlands, July 2017July, 7-10, 2017.
V. Cevher; Y.-h. Li; I. Bogunovic; L. Baldassarre; J. Scarlett et al. ; Learning-based subsampling. US2017109650 . 2017.
V. Cevher; M. Kapralov; J. Scarlett; A. Zandieh : An Adaptive Sublinear-Time Block Sparse Fourier Transform. 2017. ACM Symposium on Theory of Computing (STOC), Montreal, June 19-23, 2017.
J. Scarlett; V. Cevher : How little does non-exact recovery help in group testing?. 2017. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, March 2017. p. 6090-6094.
J. Scarlett; V. Cevher : Lower Bounds on Active Learning for Graphical Model Selection. 2017. The 20th International Conference on Artificial Intelligence and Statistics (AISTATS 2017), Fort Lauderdale, Florida, USA, April 20-22, 2017.
J. Scarlett; V. Cevher : Limits on Support Recovery With Probabilistic Models: An Information-Theoretic Framework; IEEE Transactions on Information Theory. 2017. DOI : 10.1109/TIT.2016.2606605.
I. Bogunovic; J. Scarlett; A. Krause; V. Cevher : Truncated Variance Reduction: A Unified Approach to Bayesian Optimization and Level-Set Estimation. 2016. Conference on Neural Information Processing Systems (NIPS), Barcelona, December 5-10, 2016.
I. Bogunovic; J. Scarlett; V. Cevher : Time-Varying Gaussian Process Bandit Optimization. 2016. International Conference on Artificial Intelligence and Statistics (AISTATS), Cadiz, Spain, May 9 - 11, 2016.
J. Scarlett; V. Cevher : Partial Recovery Bounds for the Sparse Stochastic Block Model. 2016. International Symposium on Information Theory (ISIT), Barcelona, July 10-15, 2016. p. 1904-1908.
J. Scarlett; V. Cevher : Converse Bounds for Noisy Group Testing with Arbitrary Measurement Matrices. 2016. International Symposium on Information Theory (ISIT), Barcelona, July 10-15, 2016. p. 2868-2872.
J. Scarlett; V. Cevher : On the Difficulty of Selecting Ising Models with Approximate Recovery; IEEE Transactions on Signal and Information Processing over Networks. 2016. DOI : 10.1109/Tsipn.2016.2596439.
J. Scarlett; V. Cevher : Limits on Sparse Support Recovery via Linear Sketching with Random Expander Matrices. 2016. International Conference on Artificial Intelligence and Statistics (AISTATS), Cadiz, Spain, May 9-11, 2016.
L. Baldassarre; Y.-H. Li; J. Scarlett; B. Gözcü; I. Bogunovic et al. : Learning-Based Compressive Subsampling; IEEE Journal on Selected Topics in Signal Processing. 2016. DOI : 10.1109/Jstsp.2016.2548442.
J. Scarlett; V. Cevher : Phase Transitions in Group Testing. 2016. ACM-SIAM Symposium on Discrete Algorithms (SODA), Arlington, Virginia, USA, January 10-12, 2016.
J. Scarlett; A. Martinez; A. Guillén i Fàbregas : Multiuser Random Coding Techniques for Mismatched Decoding; IEEE Transactions on Information Theory. 2016. DOI : 10.1109/Tit.2016.2555317.
J. Scarlett : On the Dispersions of the Gel'fand-Pinsker Channel and Dirty Paper Coding; IEEE Transactions on Information Theory. 2015. DOI : 10.1109/Tit.2015.2449844.
J. Scarlett; A. Somekh-Baruch; A. Martinez; A. Guillén i Fàbregas : A Counter-Example to the Mismatched Decoding Converse for Binary-Input Discrete Memoryless Channels; IEEE Transactions on Information Theory. 2015. DOI : 10.1109/Tit.2015.2468719.
J. Scarlett; A. Martinez; A. Guillén i Fàbregas : The Likelihood Decoder: Error Exponents and Mismatch. 2015. IEEE International Symposium on Information Theory, Hong Kong.
J. Scarlett; V. Y. F. Tan : Second-Order Asymptotics for the Discrete Memoryless MAC with Degraded Message Sets. 2015. IEEE International Symposium on Information Theory, Hong Kong.
J. Scarlett; A. Martinez; A. Guillén i Fàbregas : Refinements of the Third-Order Term in the Fixed Error Asymptotics of Constant-Composition Codes. 2015. IEEE International Symposium on Information Theory, Hong Kong.
J. Scarlett; V. Cevher : Limits on Support Recovery with Probabilistic Models: An Information-Theoretic Framework. 2015. International Symposium on Information Theory, Hong Kong, June 2015.
J. Scarlett; A. Martinez; A. Guillen I Fabregas : Second-Order Rate Region of Constant-Composition Codes for the Multiple-Access Channel; IEEE Transactions on Information Theory. 2015. DOI : 10.1109/Tit.2014.2371026.
I. Bogunovic; V. Cevher; J. Haupt; J. Scarlett : Active Learning of Self-concordant like Multi-index Functions. 2015. 40th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, Australia, April 19-24, 2015.
Y.-H. Li; J. Scarlett; P. Ravikumar; V. Cevher : Sparsistency of $\ell_1$-Regularized $M$-Estimators. 2015. The 18th International Conference on Artificial Intelligence and Statistics, San Diego, California, USA, May 9-12, 2015.
J. Scarlett; V. Y. F. Tan : Second-order asymptotics for the Gaussian MAC with degraded message sets; IEEE Transactions on Information Theory. 2015. DOI : 10.1109/Tit.2015.2487340.
A. Martinez; J. Scarlett; M. Dalai; A. Guillén i Fàbregas : A complex-integration approach to the saddlepoint approximation for random-coding bounds. 2014. International Symposium on Wireless Communications Systems, Barcelona, Spain. DOI : 10.1109/ISWCS.2014.6933428.
J. Scarlett; A. Martinez; A. Guillén i Fàbregas : Mismatched multi-letter successive decoding for the multiple-access channel. 2014. IEEE International Symposium on Information Theory, Honolulu, Hawaii, USA. DOI : 10.1109/ISIT.2014.6875292.
J. Scarlett : On the dispersion of dirty paper coding. 2014. IEEE International Symposium on Information Theory, Honolulu, Hawaii, USA. DOI : 10.1109/ISIT.2014.6875240.
J. Scarlett; A. Martinez; A. Guillén i Fàbregas : The saddlepoint approximation: Unified random coding asymptotics for fixed and varying rates. 2014. IEEE International Symposium on Information Theory, Honolulu, Hawaii, USA. DOI : 10.1109/ISIT.2014.6875162.
J. Scarlett : Second-order rate of constant-composition codes for the Gel’fand-Pinsker channel. 2014. International Zurich Seminar on Communications, Zurich, Switzerland.
J. Scarlett; L. Peng; N. Merhav; A. Martinez; A. Guillén i Fàbregas : Expurgated Random-Coding Ensembles: Exponents, Refinements, and Connections; IEEE Transactions on Information Theory. 2014. DOI : 10.1109/TIT.2014.2322033.
J. Scarlett; A. Martinez; A. Guillén i Fàbregas : Mismatched decoding: Error exponents, second-order rates and saddlepoint approximations; IEEE Transactions on Information Theory. 2014. DOI : 10.1109/TIT.2014.2310453.
J. Scarlett; A. Martinez; A. Guillén i Fàbregas : A derivation of the asymptotic random-coding prefactor. 2013. 51st Allerton Conference on Communication, Control, and Computing, Monticello, Illinois, USA. DOI : 10.1109/Allerton.2013.6736628.
J. Scarlett; A. Martinez; A. Guillén i Fàbregas : Superposition codes for mismatched decoding. 2013. IEEE International Symposium on Information Theory, Istanbul, Turkey. DOI : 10.1109/ISIT.2013.6620192.
J. Scarlett; A. Martinez; A. Guillén i Fàbregas : The mismatched multiple-access channel: General alphabets. 2013. IEEE International Symposium on Information Theory, Istanbul, Turkey. DOI : 10.1109/ISIT.2013.6620193.
J. Scarlett; A. Martinez; A. Guillén i Fàbregas : Cost-constrained random coding and applications. 2013. Information Theory and Applications Workshop, La Jolla, California, USA. DOI : 10.1109/ITA.2013.6502939.
J. Scarlett; J. Evans; S. Dey : Compressed sensing with prior information: Information-theoretic limits and practical decoders; IEEE Transactions on Signal Processing. 2013. DOI : 10.1109/TSP.2012.2225051.
J. Scarlett; A. Guillén i Fàbregas : An achievable error exponent for the mismatched multiple-access channel. 2012. 50th Allerton Conference on Communication, Control, and Computing, Monticello, Illinois, USA. DOI : 10.1109/Allerton.2012.6483464.
J. Scarlett; A. Martinez; A. Guillén i Fàbregas : Ensemble-tight error exponents for mismatched decoders. 2012. 50th Allerton Conference on Communication, Control, and Computing, Monticello, Illinois, USA. DOI : 10.1109/Allerton.2012.6483461.
J. Scarlett; J. Evans; S. Dey : How much training is needed in fading multiple access channels?. 2011. International Symposium on Wireless Communication Systems, Aachen, Germany. DOI : 10.1109/ISWCS.2011.6125414.