Locality-sensitive binary codes from shift-invariant kernels M Raginsky, S Lazebnik Advances in neural information processing systems 22, 2009 | 808 | 2009 |
Non-convex learning via stochastic gradient langevin dynamics: a nonasymptotic analysis M Raginsky, A Rakhlin, M Telgarsky Conference on Learning Theory, 1674-1703, 2017 | 554 | 2017 |
Information-theoretic analysis of generalization capability of learning algorithms A Xu, M Raginsky Advances in neural information processing systems 30, 2017 | 433 | 2017 |
Supervised learning of quantizer codebooks by information loss minimization S Lazebnik, M Raginsky IEEE transactions on pattern analysis and machine intelligence 31 (7), 1294-1309, 2008 | 281 | 2008 |
Concentration of measure inequalities in information theory, communications, and coding M Raginsky, I Sason Foundations and Trends® in Communications and Information Theory 10 (1-2), 1-246, 2013 | 272 | 2013 |
Minimax statistical learning with wasserstein distances J Lee, M Raginsky Advances in Neural Information Processing Systems 31, 2018 | 196 | 2018 |
Neural stochastic differential equations: Deep latent gaussian models in the diffusion limit B Tzen, M Raginsky arXiv preprint arXiv:1905.09883, 2019 | 189 | 2019 |
Compressed sensing performance bounds under Poisson noise M Raginsky, RM Willett, ZT Harmany, RF Marcia IEEE Transactions on Signal Processing 58 (8), 3990-4002, 2010 | 185 | 2010 |
Strong Data Processing Inequalities and-Sobolev Inequalities for Discrete Channels M Raginsky IEEE Transactions on Information Theory 62 (6), 3355-3389, 2016 | 130 | 2016 |
Markov--Nash equilibria in mean-field games with discounted cost N Saldi, T Basar, M Raginsky SIAM Journal on Control and Optimization 56 (6), 4256-4287, 2018 | 116 | 2018 |
Sequential anomaly detection in the presence of noise and limited feedback M Raginsky, RM Willett, C Horn, J Silva, RF Marcia IEEE Transactions on Information Theory 58 (8), 5544-5562, 2012 | 113 | 2012 |
Information-theoretic analysis of stability and bias of learning algorithms M Raginsky, A Rakhlin, M Tsao, Y Wu, A Xu 2016 IEEE Information Theory Workshop (ITW), 26-30, 2016 | 96 | 2016 |
Theoretical guarantees for sampling and inference in generative models with latent diffusions B Tzen, M Raginsky Conference on Learning Theory, 3084-3114, 2019 | 94 | 2019 |
Information-based complexity, feedback and dynamics in convex programming M Raginsky, A Rakhlin IEEE Transactions on Information Theory 57 (10), 7036-7056, 2011 | 94 | 2011 |
A fidelity measure for quantum channels M Raginsky Physics Letters A 290 (1-2), 11-18, 2001 | 89 | 2001 |
Stochastic dual averaging for decentralized online optimization on time-varying communication graphs S Lee, A Nedić, M Raginsky IEEE Transactions on Automatic Control 62 (12), 6407-6414, 2017 | 84 | 2017 |
Continuous-time stochastic mirror descent on a network: Variance reduction, consensus, convergence M Raginsky, J Bouvrie 2012 IEEE 51st IEEE Conference on Decision and Control (CDC), 6793-6800, 2012 | 71 | 2012 |
Online Markov decision processes with Kullback–Leibler control cost P Guan, M Raginsky, RM Willett IEEE Transactions on Automatic Control 59 (6), 1423-1438, 2014 | 66 | 2014 |
Operational distance and fidelity for quantum channels VP Belavkin, GM D’Ariano, M Raginsky Journal of mathematical physics 46 (6), 2005 | 65 | 2005 |
Performance bounds for expander-based compressed sensing in Poisson noise M Raginsky, S Jafarpour, ZT Harmany, RF Marcia, RM Willett, ... IEEE Transactions on Signal Processing 59 (9), 4139-4153, 2011 | 60 | 2011 |