Manuscripts

• V. Shah, A. Joshi, S. Ghoshal, B. Pokuri, B. Ganapathysubramaniam, S. Sarkar, C. Hegde Encoding Invariances in Deep Generative Models, June 2019.

• M. Cho, M. Soltani, C. Hegde One-Shot Neural Architecture Search via Compressive Sensing, June 2019.

• C. Hegde, F. Keinert, and E. Weber, A Kaczmarz Algorithm for Solving Tree Based Distributed Systems of Equations, April 2019.

• Z. Jiang, A. Balu, C. Hegde, and S. Sarkar, On Consensus-Optimality Trade-offs in Collaborative Deep Learning, May 2018.

• M. Soltani and C. Hegde, Fast Low-Rank Matrix Estimation without the Condition Number, December 2017.

Journal papers

1. T. Nguyen, R. Wong, and C. Hegde, Provably Accurate Double-Sparse Coding, to appear in Journal of Machine Learning Research (JMLR), 2019.

2. G. Jagatap, Z. Chen, S. Nayer, C. Hegde, and N. Vaswani, Sub-diffraction Super-resolution Imaging for Structured Data, to appear in IEEE Transactions on Computational Imaging, 2019.

3. P. Chakraborty, J. Merickel, V. Shah, A. Sharma, C. Hegde, C. Desouza, A. Drinzic, P. Gunaratne, and M. Rizzo, Quantifying Vehicle Control from Physiology in Type-1 Diabetes, to appear in Traffic Injury Prevention, (TIP), 2019.

4. P. Chakraborty, C. Hegde, and A. Sharma, Data-driven parallelizable traffic incident detection using spatio-temporally denoised robust thresholds, Transportation Research Part-C, vol. 105, p81-99, August 2019.

5. M. Soltani and C. Hegde, Fast and Provable Algorithms for Learning Two-Layer Polynomial Neural Networks, IEEE Transactions on Signal Processing, vol. 67, no. 13, p3361-3371, July 2019.

6. G. Jagatap and C. Hegde, Sample Efficient Algorithms for Recovering Structured Signals from Magnitude-Only Measurements, IEEE Transactions on Information Theory, vol. 65, no. 7, p4434-4456, July 2019.

7. M. Soltani and C. Hegde, Fast Algorithms for Demixing Sparse Signals from Nonlinear Observations, IEEE Transactions on Signal Processing, vol. 65, no. 16, p4209-4222, August 2017.

8. C. Hegde, P. Indyk, and L. Schmidt, Fast Algorithms for Structured Sparsity, Bulletin of the EATCS, no. 117, p197-228, October 2015.

9. C. Hegde, A. C. Sankaranarayanan, W. Yin, and R. G. Baraniuk, NuMax: A Convex Approach for Learning Near-Isometric Linear Embeddings, IEEE Transactions on Signal Processing, vol. 63, no. 22, p6109-6121, November 2015.

10. C. Hegde, P. Indyk, and L. Schmidt, Approximation Algorithms for Model-Based Compressive Sensing, IEEE Transactions on Information Theory, vol. 61, no. 9, p5129-5147, September 2015.

11. Y. Li, C. Hegde, A. C. Sankaranarayanan, R. G. Baraniuk, and K. F. Kelly, Compressive Image Acquisition and Classification via Secant Projections, Journal of Optics, vol. 17, no. 6, June 2015.

12. S. Nagaraj, C. Hegde, A. C. Sankaranarayanan, and R. G. Baraniuk, Optical Flow-Based Transport on Image Manifolds, Applied and Computational Harmonic Analysis, vol. 36, no. 2, p280-301, March 2014.

13. C. Hegde and R. G. Baraniuk, Signal Recovery on Incoherent Manifolds, IEEE Transactions on Information Theory, vol. 58, no. 12, p7204-7214, December 2012.

14. C. Hegde and R. G. Baraniuk, Sampling and Recovery of Pulse Streams, IEEE Transactions on Signal Processing, vol. 59, no. 4, p1505-1517, April 2011.

15. M. A. Davenport, C. Hegde, M. F. Duarte, and R. G. Baraniuk, Joint Manifolds for Data Fusion, IEEE Transactions on Image Processing, vol. 19, no. 10, p2580-2594, October 2010.

16. R. G. Baraniuk, V. Cevher, M. F. Duarte, and C. Hegde, Model-Based Compressive Sensing, IEEE Transactions on Information Theory, vol. 56, no. 4, p1982-2001, April 2010.

Conference and workshop papers

1. A. Joshi, M. Cho, V. Shah, B. Pokuri, S. Sarkar, B. Ganapathysubramanian, C. Hegde, InvNets: Encoding Statistical and Geometric Constraints in Deep Generative Models, AAAI Conference on Artificial Intelligence (AAAI), February 2020.

2. X. Lee, S. Ghadai, K. Tan, C. Hegde, S. Sarkar, Spatiotemporally Constrained Action Space Attacks on Deep Reinforcement Learning Agents, AAAI Conference on Artificial Intelligence (AAAI), February 2020.

3. G. Jagatap and C. Hegde, Algorithmic Guarantees for Inverse Imaging with Untrained Network Priors, Neural Information Processing Systems (NeurIPS), December 2019.

4. V. Shah and C. Hegde, Signal Reconstruction from Modulo Observations, IEEE GlobalSIP, November 2019.

5. A. Joshi, A. Mukherjee, S. Sarkar, and C. Hegde, Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifiers, International Conference on Computer Vision (ICCV), October 2019.

6. V. Shah, J. Merickel, P. Chakraborty, C. Hegde, A. Sharma, C. Desouza, A. Drincic, P. Gunaratne, and M. Rizzo. Quantifying driver speed behavior from real-time physiology in type 1 diabetes, Intl. Symp. Future Active Safety Technology (FastZero), September 2019.

7. J. Merickel, V. Shah, P. Chakraborty, C. Hegde, A. Sharma, C. Desouza, A. Drincic, P. Gunaratne, and M. Rizzo. Impact of physiology and environment on vehicle control behavior in drivers with type 1 diabetes, Intl. Symp. Future Active Safety Technology (FastZero), September 2019.

8. G. Jagatap and C. Hegde, Linearly Convergent Algorithms for Learning Shallow Residual Networks, International Symposium on Information Theory (ISIT), July 2019.

9. T. Nguyen, A. Soni, and C. Hegde, Tractable Learning of Sparsely Used Dictionaries from Incomplete Samples, Sampling Theory and Applications (SampTA), July 2019.

10. A. Mukherjee, A. Joshi, S. Sarkar, and C. Hegde, Attribute-Controlled Traffic Data Augmentation Using Conditional Generative Models, CVPR Workshop on Vision for All Seasons (VAS), June 2019.

11. M. Cho and C. Hegde, Reducing the Search Space for Hyperparameter Optimization Using Group Sparsity, International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2019.

12. R. Hyder, V. Shah, C. Hegde, and S. Asif Alternating Phase Projected Gradient Descent With Generative Priors for Compressive Phase Retrieval, International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2019.

13. T. Nguyen, R. Wong, and C. Hegde, On the Dynamics of Gradient Descent for Autoencoders, Artificial Intelligence and Statistics (AISTATS), April 2019.

14. R. Singh, V. Shah, B. Pokuri, B. Ganapathysubramaniam, S. Sarkar, C. Hegde Physics-aware Deep Generative Models for Creating Synthetic Microstructures, NIPS Workshop on Machine Learning for Molecules and Materials (MLMM), December 2018.

15. P. Chakraborty, A. Sharma, and C. Hegde, Freeway Traffic Incident Detection from Cameras: A Semi-Supervised Learning Approach, International Conference on Intelligent Transportation Systems (ITSC), November 2018.

16. S. Asif and C. Hegde, Phase Retrieval for Signals in Unions of Subspaces, IEEE GlobalSIP, November 2018.

17. C. Hegde, Algorithmic Aspects of Inverse Problems Using Generative Models, Allerton Conference on Communication, Control, and Computing, October 2018.

18. G. Jagatap, Z. Chen, C. Hegde, and N. Vaswani, Model-Corrected Low-Rank Ptychography, International Conference on Image Processing (ICIP), October 2018.

19. T. Nguyen, A. Soni, and C. Hegde, On Learning Sparsely Used Dictionaries from Incomplete Samples, International Conference on Machine Learning (ICML), July 2018.

20. Z. Jiang, A. Balu, C. Hegde, and S. Sarkar, Incremental Consensus-based Collaborative Deep Learning, ICML Workshop on Nonconvex Optimization in Machine Learning, July 2018. *Spotlight.*

21. G. Jagatap and C. Hegde, Towards Sample-Optimal Methods for Solving Random Quadratic Equations with Structure, International Symposium on Information Theory (ISIT), June 2018.

22. M. Soltani and C. Hegde, Fast Low-Rank Matrix Estimation for Ill-Conditioned Matrices, International Symposium on Information Theory (ISIT), June 2018.

23. M. Soltani and C. Hegde, Towards Provable Learning of Polynomial Neural Networks Using Low-Rank Matrix Estimation, Artificial Intelligence and Statistics (AISTATS), April 2018. *Oral presentation.*

24. V. Shah and C. Hegde, Solving Linear Inverse Problems Using GAN Priors: An Algorithm with Provable Guarantees, International Conference on Acoustics, Speech, and Signal Processing (ICASSP), April 2018.

25. G. Jagatap, Z. Chen, C. Hegde, and N. Vaswani, Sub-Diffraction Imaging Using Fourier Ptychography and Structured Sparsity, International Conference on Acoustics, Speech, and Signal Processing (ICASSP), April 2018. *Oral presentation.*

26. Z. Chen, G. Jagatap, S. Nayer, C. Hegde, and N. Vaswani, Low-Rank Fourier Ptychography, International Conference on Acoustics, Speech, and Signal Processing (ICASSP), April 2018.

27. T. Nguyen, R. Wong, and C. Hegde, A Provable Approach for Double-Sparse Coding, AAAI Conference on Artificial Intelligence (AAAI), February 2018. *Oral presentation.*

28. G. Jagatap and C. Hegde, Fast, Sample-Efficient Algorithms for Structured Phase Retrieval, Neural Information Processing Systems (NIPS), December 2017.

29. Z. Jiang, A. Balu, C. Hegde, and S. Sarkar, Collaborative Deep Learning in Fixed Topology Networks, Neural Information Processing Systems (NIPS), December 2017.

30. A. Balu, T. Nguyen, A. Kokate, C. Hegde, and S. Sarkar, A Forward-Backward Approach for Visualizing Information Flow in Deep Networks, NIPS Symposium on Interpretable Machine Learning, December 2017.

31. M. Cohen, C. Hegde, S. Jegelka, and L. Schmidt, Efficiently Optimizing over (Non-Convex) Cones via Approximate Projections, NIPS Workshop on Optimization for Machine Learning (OPT), December 2017. *Oral presentation.*

32. P. Chakraborty, C. Hegde, and A. Sharma, Trend Filtering in Network Time Series, with Applications to Traffic Incident Detection, NIPS Time Series Workshop (TSW), December 2017.

33. C. Hubbard and C. Hegde, Parallel Computing Heuristics for Matrix Completion, IEEE GlobalSIP Symposium on Accelerating Deep Learning, November 2017.

34. M. Soltani and C. Hegde, Demixing Structured Superpositions from Periodic and Aperiodic Nonlinear Observations, IEEE GlobalSIP Symposium on Compressed Sensing and Deep Learning, November 2017.

35. V. Shah, M. Soltani and C. Hegde, Reconstruction from Periodic Nonlinearities, with Applications to HDR Imaging, Asilomar Conference on Signals, Systems, and Computers, November 2017.

36. M. Soltani and C. Hegde, Fast Algorithms for Learning Latent Variables in Graphical Models, ACM KDD Mining and Learning With Graphs (KDD MLG), August 2017.

37. B. Wang, C. Gan, J. Yang, C. Hegde, J. Wu, Graph-Based Multiple-Line Outages in Power Transmission Systems, IEEE PES General Meeting (PES-GM), July 2017.

38. M. Soltani and C. Hegde, Stable Recovery from Random Sinusoidal Feature Maps, International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2017.

39. C. Hegde, P. Indyk, and L. Schmidt, Fast Recovery from a Union of Subspaces, Neural Information Processing Systems (NIPS), December 2016.

40. M. Soltani and C. Hegde, Iterative Thresholding for Demixing Structured Superpositions in High Dimensions, NIPS Workshop on Learning in High Dimensions with Structure (LHDS), December 2016. *Oral presentation.*

41. M. Soltani and C. Hegde, A Fast Iterative Algorithm for Demixing Sparse Signals from Nonlinear Observations, IEEE GlobalSIP Symposium on Compressed Sensing and Deep Learning, December 2016.

42. M. Soltani and C. Hegde, Demixing Sparse Signals from Nonlinear Observations, Asilomar Conference on Signals, Systems, and Computers, November 2016.

43. C. Hubbard, J. Bavslik, C. Hegde, and C. Hu, Data-Driven Prognostics of Li-Ion Rechargeable Battery using Bilinear Kernel Regression, Annual Conference of the Prognostics and Health Management Society (PHM), October 2016.

44. C. Hegde, P. Indyk, and L. Schmidt, A Nearly Linear-Time Framework for Graph-Structured Sparsity, International Joint Conferences on Artificial Intelligence (IJCAI), Sister Conference Best Paper Track, July 2016. (Invited paper)
    

45. C. Hegde, Bilevel Feature Selection in Nearly-Linear Time, IEEE Statistical Signal Processing Workshop (SSP), June 2016.
    

46. C. Hegde, A Fast Algorithm for Demixing Signals with Structured Sparsity, International Conference on Signal Processing and Communications (SPCOM), June 2016. (Invited paper)
    

47. C. Hegde, P. Indyk, and L. Schmidt, A Nearly Linear-Time Framework for Graph-Structured Sparsity, International Conference on Machine Learning (ICML), July 2015.
    *Winner of the Best Paper Award. *

48. J. Acharya, I. Diakonikolas, C. Hegde, J. Li, L. Schmidt, Fast and Near-Optimal Algorithms for Approximating Distributions by Histograms, ACM Symposium on Principles of Database Systems (PODS), May 2015.

49. M. Araya, C. Hegde, P. Indyk, and L. Schmidt, Greedy Strategies for Data Adaptive Shot Selection, Proc. EAGE Annual Meeting, May 2015.

50. L. Schmidt, C. Hegde, P. Indyk, L. Lu, X. Chi, and D. Hohl, Seismic Feature Extraction Using Steiner-Tree Methods, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), April 2015.

51. C. Hegde, P. Indyk, and L. Schmidt, Nearly Linear-Time Model-Based Compressive Sensing, International Colloquium on Automata, Languages, and Programming (ICALP), July 2014.

52. C. Hegde, P. Indyk, and L. Schmidt, A Fast Algorithm for Tree-Sparse Recovery, International Symposium on Information Theory (ISIT), June 2014.

53. C. Hegde, A. C. Sankaranarayanan, and R. G. Baraniuk, Lie Operators for Compressive Sensing, International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2014.

54. L. Schmidt, C. Hegde, P. Indyk, J. Kane, L. Lu, D. Hohl, Automatic Fault Localization Using the Generalized Earth Movers Distance Model, International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2014.

55. C. Hegde, P. Indyk, and L. Schmidt, Approximation-Tolerant Model-Based Compressive Sensing, ACM Symposium on Discrete Algorithms (SODA), January 2014.

56. E. Grant, C. Hegde, and P. Indyk, Nearly Optimal Linear Embeddings into Very Low Dimensions, IEEE GlobalSIP Symposium on Sensing and Statistical Inference, December 2013.

57. L. Schmidt, C. Hegde, and P. Indyk, The Constrained Earth Movers Distance Model, with Applications to Compressive Sensing, Sampling Theory and Applications (SampTA), July 2013.

58. C. Hegde, A. C. Sankaranarayanan, and R. G. Baraniuk, Learning Measurement Matrices for Redundant Dictionaries, Signal Processing with Adaptive Sparse Structured Representations (SPARS), July 2013.

59. Y. Li, C. Hegde, R. G. Baraniuk, and K. F. Kelly, Compressive Classification via Secant Projections, Computational Optical Sensing and Imaging (COSI), June 2013.

60. D. K. Grady, M. Moll, C. Hegde, A. C. Sankaranarayanan, R. G. Baraniuk, and L. E. Kavraki, Multi-Robot Target Verification with Reachability Constraints , IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), November 2012.

61. D. K. Grady, M. Moll, C. Hegde, A. C. Sankaranarayanan, R. G. Baraniuk, and L. E. Kavraki, Multi-Objective Sensor Replanning for a Car-Like Robot, IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), November 2012.

62. C. Hegde, A. C. Sankaranarayanan, and R. G. Baraniuk, Near-Isometric Linear Embeddings of Manifolds, IEEE Statistical Signal Processing Workshop (SSP), August 2012.

63. C. Hegde and R. G. Baraniuk, SPIN: Iterative Signal Recovery on Incoherent Manifolds, IEEE International Symposium on Information Theory (ISIT), July 2012.

64. D. K. Grady, M. Moll, C. Hegde, A. C. Sankaranarayanan, R. G. Baraniuk, and L. E. Kavraki, Look Before You Leap: Predictive Sensing and Opportunistic Navigation, IROS Workshop on Open Problems in Motion Planning, September 2011.

65. A. C. Sankaranarayanan, C. Hegde, S. Nagaraj, and R. G. Baraniuk, Go with the Flow: Optical Flow-based Transport Operators for Image Manifolds, Allerton Conference on Communication, Control, and Computing, September 2011.

66. M. A. Davenport, C. Hegde, M. F. Duarte, and R. G. Baraniuk, High-Dimensional Data Fusion via Joint Manifold Learning, AAAI Fall Symposium on Manifold Learning, November 2010.

67. C. Hegde and R. G. Baraniuk, Compressive Sensing of a Superposition of Pulses, International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2010.

68. S. R. Schelle, J. N. Laska, C. Hegde, M. F. Duarte, M. A. Davenport, and R. G. Baraniuk, Texas Hold 'Em Algorithms for Distributed Compressive Sensing, International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2010.

69. C. Hegde and R. G. Baraniuk, Compressive Sensing of Streams of Pulses, Allerton Conference on Communication, Control, and Computing, September 2009.

70. V. Cevher, P. Indyk, C. Hegde, and R. G. Baraniuk, Recovery of Clustered Sparse Signals from Compressive Measurements, Sampling Theory and Applications (SampTA), May 2009.

71. C. Hegde, M. F. Duarte, and V. Cevher, Compressive Sensing Recovery of Spike Trains Using a Structured Sparsity Model, Signal Processing with Adaptive Sparse Structured Representations (SPARS), April 2009.
    *Winner of the Best Student Paper Award.*

72. M. F. Duarte, C. Hegde, V. Cevher, and R. G. Baraniuk, Recovery of Compressible Signals in Unions of Subspaces, Conference on Information Sciences and Systems (CISS), March 2009.

73. V. Cevher, M. F. Duarte, C. Hegde, and R. G. Baraniuk, Sparse Signal Recovery Using Markov Random Fields, Neural Information Processing Systems (NIPS), December 2008.

74. C. Hegde, M. B. Wakin, and R. G. Baraniuk , Random Projections for Manifold Learning, Neural Information Processing Systems (NIPS), December 2007.

75. M. A. Davenport, C. Hegde, M. B. Wakin, and R. G. Baraniuk, Manifold-Based Approaches for Improved Classification , NIPS Workshop on Topology Learning, December 2007.

76. C. Hegde, M. A. Davenport, M. B. Wakin, and R. G. Baraniuk, Efficient Machine Learning Using Random Projections, NIPS Workshop on Efficient Machine Learning, December 2007.

Thesis

• C. Hegde, Nonlinear Signal Models: Geometry, Algorithms, and Analysis
  Ph.D. thesis, ECE Department, Rice University, September 2012.
  *Winner of Ralph Budd Award for Best Thesis in the School of Engineering.*

Books, book chapters, and monographs

• C. Hegde and A. Kamal, Theoretical Foundations of Computer Engineering, Compiled lecture notes, 2017.

• C. Hegde, Principles of Data Analytics, Compiled lecture notes, 2017.

• R. G. Baraniuk, M. A. Davenport, M. F. Duarte, and C. Hegde, An Introduction to Compressive Sensing, Connexions e-textbook, 2011.

Technical reports

1. G. Jagatap and C. Hegde, Learning ReLU Networks via Alternating Minimization, June 2018.

2. T. Nguyen, R. Wong, and C. Hegde, Autoencoders Learn Generative Linear Models, June 2018.

3. M. Soltani and C. Hegde, Improved Algorithms for Matrix Recovery from Rank-One Projections, May 2017.

4. C. Hubbard and C. Hegde, GPUFish: A Parallel Computing Framework for Matrix Completion from A Few Observations, November 2016.

5. C. Hegde, Bilevel Feature Selection in Nearly-Linear Time, February 2016.

6. C. Hegde, A. C. Sankaranarayanan, and R. G. Baraniuk, Learning Manifolds in the Wild, July 2012.

7. M. Soltani and C. Hegde, Demixing Sparse Signals from Nonlinear Observations, Iowa State University Technical Report, March 2016.

8. C. Hegde, O. C. Tuzel, and F. Porikli, Efficient Upsampling of Natural Images, MERL Technical Report, March 2012.

9. M. A. Davenport, C. Hegde, M. F. Duarte, and R. G. Baraniuk, A Theoretical Analysis of Joint Manifolds, Rice University ECE Technical Report TREE0901, January 2009.

10. C. Hegde, M. B. Wakin, and R. G. Baraniuk, Random Projections for Manifold Learning: Proofs and Analysis, Rice University ECE Technical Report TREE0710, October 2007.