Home Page of Subhro Ghosh

Subhro Ghosh
Dean's Chair Associate Professor
National University of Singapore
Department of Mathematics
Dept of Statistics and Data Science (by courtesy)
Dept of Computer Science (by courtesy)
NUS AI Institute & Institute of Data Science

Email:
< subhrowork (**at**) gmail.com > || < matghos (**at**) nus.edu.sg >

About me

Research

Selected recognitions

• Dean's Chair Associate Professorship, NUS, 2025


• Finalist for the Bell Labs Prize, 2022


• Singapore MOE Tier II Grant, 2022 (~ US$ 500 K +)
  Complex structures in Statistical Physics and the Math of Data


• Gold Medal for M.Math., Indian Statistical Institute


• Gold Medal for B.Stat., Indian Statistical Institute

Editorial

• Advances in Applied Probability
  
• Journal of Applied Probability
  
• Sankhya - The Indian Journal of Statistics (official journal of the Indian Statistical Institute)

Selected and recent works

• Gaussian determinantal processes: A new model for directionality in data, with P. Rigollet,
  Proceedings of the National Academy of Sciences (PNAS), vol. 117, no. 24, pp. 13207--13213
  (Direct Submission)
  article


• Sparse Multi-Reference Alignment: Phase Retrieval, Uniform Uncertainty Principles and the Beltway Problem, with P. Rigollet
  Foundations of Computational Math. (FoCM) 23, no. 5 : 1851-1898
  preprint


• State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives, with HS Tran, P Gupta, R Bardenet
  NeurIPS 2026, to appear
  preprint


• Small coresets via negative dependence: DPPs, linear statistics, and concentration, with R. Bardenet, H. Simon-Onfroy, H.S. Tran
  Spotlight at NeurIPS 2024
  Advances in Neural Information Processing Systems , 37: 84329-84349
  preprint


• Determinantal point processes based on orthogonal polynomials for sampling minibatches in SGD, with R. Bardenet, M. Lin
  Spotlight at NeurIPS 2021
  Advances in Neural Information Processing Systems , 34, 16226-16237
  preprint


• Approximate Gibbsian structure in strongly correlated point fields and generalized Gaussian zero ensembles, with U. Gangopadhyay, K.A. Tan
  Communications in Pure Appl. Math. (CPAM) 77, no. 8 : 3427-3519
  preprint


• Gaussian complex zeros on the hole event: the emergence of a forbidden region, with A. Nishry,
  Communications in Pure Appl. Math. (CPAM), 72, no. 1 : 3-62
  preprint


• Rigidity and Tolerance in point processes: Gaussian zeroes and Ginibre eigenvalues, with Y. Peres,
  Duke Mathematical Journal, 166 (10), 1789-1858
  preprint


• Determinantal processes and completeness of random exponentials: the critical case,
  Probability Theory and Related Fields (PTRF), 163 (3-4), 643-665
  preprint


• Continuum Percolation for Gaussian zeroes and Ginibre eigenvalues, with M. Krishnapur, Y. Peres,
  Annals of Probability, 44 (5), 3357-3384
  preprint


• Maximum Likelihood under constraints: Degeneracies and Random Critical Points, with S. Chaudhuri, U. Gangopadhyay
  IEEE Transactions on Information Theory , vol. 69, no. 12, pp. 7976-7997
  preprint


• Signal Analysis via the Stochastic Geometry of Spectrogram Level Sets , with M. Lin, D. Sun
  IEEE Transactions on Signal Processing, 70 : 1104-1117.
  preprint


• Fractal Gaussian Networks: A sparse random graph model based on Gaussian Multiplicative Chaos, with K. Balasubramanian, X. Yamg,
  IEEE Transactions on Information Theory, 68 (5), 3234-3252
  International Conference on Machine Learning (ICML), PMLR Vol. 119 3545--3555
  preprint
  
  
• Disordered complex networks: energy optimal lattices and persistent homology, with N. Miyoshi, T. Shirai,
  IEEE Transactions on Information Theory, 68 (8), 5513-5534
  preprint


• Generative Principal Component Analysis , with Z. Liu, J. Liu, J. Han, J. Scarlett,
  International Conference on Learning Representations (ICLR), 2022
  preprint


• Generalized stealthy hyperuniform processes: maximal rigidity and the bounded holes conjecture, with J.L. Lebowitz,
  Communications in Mathematical Physics (CMP), 363, no. 1 : 97-110
  preprint


• Fluctuation and Entropy in Spectrally Constrained random fields, with K. Adhikari, J.L. Lebowitz,
  Communications in Mathematical Physics (CMP), 386, 749–780 .
  preprint


• Rigidity hierarchy in random point fields: random polynomials and determinantal processes, with M. Krishnapur,
  Communications in Mathematical Physics (CMP), 388, no. 3 : 1205-1234.
  preprint


• Dictionary Learning under Symmetries via Group Representations, with A. Low, Y.S. Soh, Z. Feng, B. Tan
  Applied and Computational Harmonic Analysis (ACHA) , 101855 (2026)
  preprint


• Filtering through a topological lens: homology for point processes on the time-frequency plane, with J. Miramont, K.A. Tan, S.S. Mukherjee, R. Bardenet
  preprint


• Implicit regularization via Spectral Neural Networks and non-linear matrix sensing, with H.T.M. Chu, C.T. Lam, S.S. Mukherjee
  preprint


• Negative Dependence as a toolbox for machine learning: review and new developments, with H.S. Tran, V. Petrovic, R. Bardenet
  preprint


• On the Statistical Optimality of Optimal Decision Trees, with Z Xu, YS Tan
  preprint


• Maximum entropy based testing in network models: ERGMs and constrained optimization, with RN Karmakar, S Lahiry
  preprint


• Gaussian mixtures and non-parametric likelihoods through the lens of statistical mechanics, with A Guntuboyina, S Mukherjee, HS Tran
  preprint


• Fast determinantal sampling on general spaces and diffusion geometry, with HS Tran, P Gupta
  preprint


• A statistical approach to bias in zero-shot learning: the lens of handwriting recognition, with C Chew, GS Chia, S Chanda, SS Mukherjee
  preprint


• Gradient Descent with Stochastic Subspaces via Persistence of Memory, with CZQ Ng, PL Poirion, A Takeda
  preprint


Back to top

Research Grants and major organisational activities

Complex structures in Statistical Physics and the Math of Data (~ US$ 500 K +) [Singapore MOE Tier II Grant; 2022-25]

The information geometry of Gaussian Mixtures: a statistical mechanics approach [Singapore MOE Tier I Grant; 2026-27]

Randomness and structure through a topological lens [Singapore MOE Tier I Grant; 2025-27]

Stochastic models with latent symmetries [Singapore MOE Tier I grant; 2024­-26]

Stochastics beyond Independence : A Math of Data Perspective [Singapore MOE Tier I Grant; 2020-24]

Resilience and Growth Programme [NUS, 2020-21]

Rigidity Phenomena in Random Processes [NUS Start Up Grant; 2017-23]





Statistical Mechanics meets Machine Learning (with F. Krzakala, B. Loureiro) [Institute for Mathematical Sciences, Singapore; 2028]

The Mathematics of Data (with A. Bandeira, P. Rigollet) [Institute for Mathematical Sciences, Singapore; 02 Jan–26 Jan 2024]

Mathematics for Machine Intelligence [One day Woskshop, Dept of Math (NUS); Apr 29, 2025]

Invited Session at 2025 INFORMS International Meeting [Singapore; Jul 20-23, 2025]

Spring School on The Mathematics of Quantum Information and Learning (with W.T. Gan, R.O. Oliviera, M. Tomamichel) [Institute for Mathematical Sciences, Singapore; Feb-Mar 2027]

Statistical Physics of interacting particle systems (with D. Dereudre, A. Hardy, M. Maida) [Institute for Mathematical Sciences, Singapore; Aug 29 -- Sep 9 2022]

Random matrices, Stochastic geometry and Related topics (with T. Shirai, K. Suzaki) [J.S.P.S., IMS Singapore & Dept. of Math. (NUS); Mar 14--16, 2019]

Conformal Field Theories: Randomness and Geometry (with T.C. Dinh, S. Ganguly) [Institute for Mathematical Sciences, Singapore; May 18--29, 2026]

Symposium on Mathematics (with T.C. Dinh) [Dept of Math (NUS); Aug 5, 2022]

A Day of Randomness: in honour of Percy Deift (with H. Huang) [Dept of Math (NUS); May 24, 2024]

The Singapore-Bangalore "What is ...?" Workshop on Mathematics (with W.T. Gan, D. Yogeshwaran, V. Pingali, S. Mukherjee, S. Lahiry) [Indian Institute of Science, Bangalore, Aug 23-34, 2025]

Oppenheim Lecture and Workshop (by Martin Hairer) (with W.T. Gan, R. Sun) [Dept of Math (NUS) & IMS, Singapore; Oct 16-26, 2024]


Back to top

Research Fellows

Satyaki Mukherjee (PhD UC Berkeley) [current]

Xiaoyu Dong (PhD University of Michigan) [current]

Samriddha Lahiry (PhD Cornell University) [current]

Akshay Hegde (PhD Oxford University) [current]

Soumendu Sundar Mukherjee (PhD UC Berkeley) [next position : Assistant Professor, Indian Statistical Institute]

Meixia Lin (PhD National University of Singapore) [next position : Assistant Professor, Singapore University of Technology and Design]

Hong T.M. Chu (PhD National University of Singapore) [next position : Assistant Professor, VinUniversity, Vietnam]

Ujan Gangopadhyay (PhD University of Southern California) [next position : Postdoc, University of Luxembourg]

Hao Wu (PhD National University of Singapore) [next position : Assistant Professor, Nanjing University, China]

Back to top

Graduate students

Hoang Son Tran (PhD, 2020 -- 26 ) [jt w/ T.C. Dinh]

Kin Aun Tan (Phd, 2022 -- )

Clement Ng (PhD, 2025 -- ; Masters by research, 2023-24 )

Clarence Chew (PhD, 2024 -- )

Chew Shia See (PhD, 2025 -- ) [jt w/ M. Mucciconi]

Martin Eppert (PhD, 2025 -- ) [jt w/ Y.S. Tan]

Kaustav Choubey (PhD, 2026 -- )

Rathindra Karmakar (Research assistant, 2024-25)

Manh Hung Tran (PhD, 2020--24 ) [jt w/ T.C. Dinh]

Xinran Bian (PhD, 2020--24 )

Gim Siang Chia (Masters by research, 2023--24)

Vladimir Petrovic (Masters by research, 2023--24)

Jingbin Pan (Masters by research, 2023--24)

Jeremiah Thomson (Masters by research, 2020 -- 2022)

Dongfang Sun (Masters by research, 2020)

Jnaneshwar Baslingekar (Research assistant, 2022)

Hugo Simon (Research assistant, 2022)

Back to top

Teaching

Tutorial at Data Science: Probabilistic and Optimization Methods, ICTS-TIFR, Bangalore [Aug 2025]

Course at the Autumn School and Workshop on Dynamics of point processes and particle systems, Münster, Germany [Nov 2024]

Course at the Darwin “Summer” School on the Mathematical Aspects of Data Science (org. ANU), Darwin, Australia [Jun 2024]

Course at Topics in High Dimensional Probability, ICTS-TIFR, Bangalore [Jan 2023]

Course at DPP-Fermions 2022, ENS de Lyon, France [Jun 2022]



Back to top

Seminar

Publications

• Gradient Descent with Stochastic Subspaces via Persistence of Memory, with CZQ Ng, PL Poirion, A Takeda
  preprint


• A statistical approach to bias in zero-shot learning: the lens of handwriting recognition, with C Chew, GS Chia, S Chanda, SS Mukherjee
  preprint


• Fast determinantal sampling on general spaces and diffusion geometry, with HS Tran, P Gupta
  preprint


• Gaussian mixtures and non-parametric likelihoods through the lens of statistical mechanics, with A Guntuboyina, S Mukherjee, HS Tran
  preprint


• State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives, with HS Tran, P Gupta, R Bardenet
  preprint


• Maximum entropy based testing in network models: ERGMs and constrained optimization, with RN Karmakar, S Lahiry
  preprint


• Filtering through a topological lens: homology for point processes on the time-frequency plane, with J. Miramont, K.A. Tan, S.S. Mukherjee, R. Bardenet
  preprint


• On the Statistical Optimality of Optimal Decision Trees, with Z Xu, YS Tan
  preprint


• Dictionary Learning under Symmetries via Group Representations, with A. Low, Y.S. Soh, Z. Feng, B. Tan
  Applied and Computational Harmonic Analysis , 101855 (2026)
  preprint


• Negative Dependence as a toolbox for machine learning: review and new developments, with H.S. Tran, V. Petrovic, R. Bardenet
  preprint


• Small coresets via negative dependence: DPPs, linear statistics, and concentration, with R. Bardenet, H. Simon-Onfroy, H.S. Tran
  Spotlight at NeurIPS 2024
  preprint


• On an Empirical Likelihood based Solution to the Approximate Bayesian Computation Problem, with S. Chaudhuri, K.C. Pham
  Statistical Analysis and Data Mining: The ASA (American Statistical Association) Data Science Journal 17, no. 5 (2024): e11711.
  preprint


• Implicit regularization via Spectral Neural Networks and non-linear matrix sensing, with H.T.M. Chu, C.T. Lam, S.S. Mukherjee
  preprint


• Minimax-optimal estimation for sparse multi-reference alignment with collision-free signals, with S.S. Mukherjee, J.B. Pan
  preprint


• Hole event for random holomorphic sections on compact Riemann surfaces, with T.C. Dinh, H. Wu,
  preprint


• Approximate Gibbsian structure in strongly correlated point fields and generalized Gaussian zero ensembles, with U. Gangopadhyay, K.A. Tan
  Communications in Pure Appl. Math., 77, no. 8 (2024): 3427-3519
  preprint


• Learning Networks from Gaussian Graphical Models and Gaussian Free Fields, with S.S. Mukherjee, H.S. Tran, U. Gangopadhyay,
  Journal of Statistical Physics , 191, no. 4 (2024): 45
  preprint


• Sparse Multi-Reference Alignment: Phase Retrieval, Uniform Uncertainty Principles and the Beltway Problem, with P. Rigollet
  Foundations of Computational Math 23, no. 5 (2023): 1851-1898
  preprint


• Maximum Likelihood under constraints: Degeneracies and Random Critical Points, with S. Chaudhuri, U. Gangopadhyay
  IEEE Transactions on Information Theory , vol. 69, no. 12, pp. 7976-7997 (2023)
  preprint


• Disordered complex networks: energy optimal lattices and persistent homology, with N. Miyoshi, T. Shirai,
  IEEE Transactions on Information Theory, 68 (8), 5513-5534 (2022)
  preprint


• Signal Analysis via the Stochastic Geometry of Spectrogram Level Sets , with M. Lin, D. Sun
  IEEE Transactions on Signal Processing, 70 (2022): 1104-1117.
  preprint


• Fractal Gaussian Networks: A sparse random graph model based on Gaussian Multiplicative Chaos, with K. Balasubramanian, X. Yang,
  IEEE Transactions on Information Theory, 68 (5), 3234-3252 (2022)
  International Conference on Machine Learning (ICML), 2020
  preprint
  
  
• Generative Principal Component Analysis , with Z. Liu, J. Liu, J. Han, J. Scarlett,
  International Conference on Learning Representations (ICLR), 2022
  preprint


• Learning with latent group sparsity via heat flow dynamics on networks, with S.S. Mukherjee,
  preprint


• Rigidity hierarchy in random point fields: random polynomials and determinantal processes, with M. Krishnapur,
  Communications in Mathematical Physics, 388, no. 3 (2021): 1205-1234.
  preprint


• Determinantal point processes based on orthogonal polynomials for sampling minibatches in SGD, with R. Bardenet, M. Lin
  Spotlight paper at NeurIPS 2021
  at Advances in Neural Information Processing Systems, 34 (2021) 16226-16237
  preprint


• Towards Sample-Optimal Compressive Phase Retrieval with Sparse and Generative Priors, with Z. Liu, J. Scarlett,
  Neural Information Processing Systems (NeurIPS), 2021
  preprint


• Fluctuation and Entropy in Spectrally Constrained random fields, with K. Adhikari, J.L. Lebowitz,
  Communications in Math. Physics, 386, 749–780 (2021).
  preprint


• Quantitative Marcinkiewicz's theorem and central limit theorems: applications to spin systems and point processes, with T.C. Dinh, H.S. Tran, M.H. Tran
  preprint


• Robust 1-bit Compressive Sensing with Partial Gaussian Circulant Matrices and Generative Priors, with Z. Liu, J. Scarlett
  IEEE Information Theory Workshop, 2021
  preprint


• Learning from DPPs via Sampling: Beyond HKPV and symmetry, with R. Bardenet
  preprint


• Transmission and Navigation on Disordered Lattice Networks, Directed Spanning Forests and Brownian Web, with K. Saha,
  Journal of Statistical Physics, vol. 180, no. 1 (2020): 1167-1205
  Special issue in honour of J.L. Lebowitz
  preprint


• Gaussian determinantal processes: A new model for directionality in data, with P. Rigollet,
  Proceedings of the National Academy of Sciences, vol. 117, no. 24 (2020), pp. 13207--13213
  article


• Gaussian complex zeros on the hole event: the emergence of a forbidden region, with A. Nishry,
  Communications in Pure Appl. Math., 72, no. 1 (2019): 3-62
  preprint


• Generalized stealthy hyperuniform processes: maximal rigidity and the bounded holes conjecture, with J.L. Lebowitz,
  Communications in Math. Physics, 363, no. 1 (2018): 97-110
  preprint


• Point processes, hole events, and large deviations: random complex zeros and Coulomb gases, with A. Nishry,
  Constructive Approximation, 48, no. 1 (2018): 101-136.
  Special Issue: Approximation and Statistical Physics – Part I
  preprint


• Fluctuations, large deviations and rigidity in hyperuniform systems: a brief survey, with J.L. Lebowitz
  Indian Journal of Pure and Applied Mathematics , vol. 48 no. 4 (2017), 609-631
  Special issue in honour of B.V. Rao
  preprint


• Rigidity and Tolerance in point processes: Gaussian zeroes and Ginibre eigenvalues, with Y. Peres,
  Duke Mathematical Journal , 1166, no. 10, 1789-1858 (2017)
  preprint


• Number rigidity in superhomogeneous random point fields, with J. L. Lebowitz,
  Journal of Statistical Physics , vol. 166 (3-4), 1016-1027 (2017)
  Special issue in honour of Y. Sinai
  preprint


• Multivariate CLT follows from strong Rayleigh property, with T. Liggett,R. Pemantle,
  Proceedings of ANALCO, SIAM, 2017
  preprint


• Continuum Percolation for Gaussian zeroes and Ginibre eigenvalues, with M. Krishnapur, Y. Peres,
  Annals of Probability, 44 (5), 3357-3384 (2016)
  preprint


• Palm measures and rigidity phenomena in point processes,
  Electronic Communications in Probability , vol. 21 (2016)
  preprint


• Large deviations for zeros of random polynomials with i.i.d. exponential coefficients, with O. Zeitouni,
  Int. Math. Res. Not., (5), 1308-1347 (2016)
  preprint


• Determinantal processes and completeness of random exponentials: the critical case,
  Probability Theory and Related Fields, 163 (3-4), 643-665 (2015)
  preprint


• Rigidity and Tolerance in Gaussian zeroes and Ginibre eigenvalues: quantitative estimates,
  preprint


• Exact quantum algorithm to distinguish Boolean functions of different weights, with S.L. Braunstein, B.S. Choi, S. Maitra,
  Journal of Physics A: Mathematical and Theoretical, Volume 40, Number 29 (2007)
  journal


• Symmetry of Bound and Antibound States in the Semiclassical Limit for a General Class of Potentials, with S. Dyatlov,
  Proc. Amer. Math. Soc. 138 (2010), 3203-3210
  preprint


• Rigidity Phenomena in random point sets
  PhD Thesis, UC Berkeley (2013)
  Thesis


Back to top

A Random Gallery