Ambedkar DUKKIPATI

Recent Work

• Predictive AI with External Knowledge Infusion for Stocks
  Ambedkar Dukkipati, Kawin Mayilvaghanan, Naveen Kumar Pallekonda, Sai Prakash Hadnoor and Ranga Shaarad Ayyagari
  [arXiv]
  
  
• Markov Decision Processes under External Temporal Processes
  Ranga Shaarad Ayyagari and Ambedkar Dukkipati
  [arXiv]
  
  
• Temporal Abstration in Reinforcement Leanring with Offline Data
  Ranga Shaarad Ayyagari, Anurita Ghosh and Ambedkar Dukkipati
  [arXiv]
  
  

2025

• Learning Long Contexts and Forecasting with Komogorov-Arnold Hawkes Processes
  Naveen Kumar Pellekonda, Prabhas Reddy Onteru, Anuj Kumar and Ambedkar Dukkipati
  IEEE International Conference on Multimedia Information Processing and Retrieval : 2025.
  
  
• Active Reinforcement Learning Strategies for Offline Policy Improvement
  Ambedkar Dukkipati, Ranga Shaarad Ayyagari, Bodhisattwa Dasgupta, Parag Dutta and Prabhas Reddy Onteru
  39th AAAI Conference on Artificial Intelligence (AAAI): 2025.
  (Oral, among top 4.6% )
  [blog]
  
  
• Deep Representation Learning for Forecasting Recursive and Multi-Relational Events in Temporal Networks
  Tony Gracious and Ambedkar Dukkipati
  39th AAAI Conference on Artificial Intelligence (AAAI): 2025.
  [blog]
  
  
• Neural Temporal Point Processes for Forecasting Directional Relations in Evolving Hypergraphs.
  Tony Gracious, Arman Gupta and Ambedkar Dukkipati
  39th AAAI Conference on Artificial Intelligence (AAAI): 2025.
  [blog]

2024

• Learning to Switch off, Switch on, and Integrate Modalities in Large Pretrained Transformers
  Tejas Duseja, Annervaz K. M, Jeevithiesh Duggani, Shyam Zacharia, Michael Free and Ambedkar Dukkipati
  IEEE International Conference on Multimedia Information Processing and Retrieval : 2024.
  
  
• Causal Feature Alignment: Learning to Ignore Spurious Background Features
  Rahul Venkataramnai, Parag Dutta, Vikram Melapudi and Ambedkar Dukkipati
  WACV: 2024.
  

2023

• Deep Representation Learning for Prediction of Temporal Event Sets in the Continuous Time Domain
  Parag Dutta, Kawin Mayilvaghanan, Pratyaksha Sinha and Ambedkar Dukkipati
  ACML: 2023.
  
  
• Risk-Aware Algorithms for Combinatorial Semi-Bandits
  Ranga Shaarad Ayyagari and Ambedkar Dukkipati
  International Symposium on Information Theory (ISIT): 2023.
  [arXiv]
  
  
• A Multi-Team Multi-Model Collaborative COVID-19 Forecasting Hub for India
  A. Adiga, S. Athreya, K. R. Bhimala, A. Dukkipati, T. Gracious, S. Gupta, B. Hurt, G. Kaur, B. Lewis, M. Marathe, V. Mudkavi, G. K. Patra, N. Rathod, R. Sundaresan, S. Venkataramanans and S. Yasodharan
  Winter Simulation Conference (WSC): 2023.
  
  
• Dynamic Representation Learning with Temporal Point Processes for Higher-Order Interaction Forecasting.
  Tony Gracious and Ambedkar Dukkipati
  37th AAAI Conference on Artificial Intelligence (AAAI): 2023.
  [link] [pdf]

2022

• Consistency of Constrained Spectral Clustering under Graph Induced Fair Planted Partitions.
  Shubham Gupta and Ambedkar Dukkipati
  Conference on Neural Information Processing Systems (NeurIPS): 2022.
  [arXiv] [pdf]
  
  
• Learning Skills to Navigate without a Master: A Sequential Multi-Policy Reinforcement Learning Algorithm.
  Ambedkar Dukkipati, Rajarshi Banerjee, Ranga Shaarad Ayyagari and Dhaval P. Udaybhai
  IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS): 2022.
  [arXiv]
  
  
• Graph Convolutional Neural Networks for Alzheimer's Classification with Transfer Learning and HPC methods
  Anoop Kumar, Vibha Balaji, M. A. Chandrashekar, Ambedkar Dukkipati, Sathish Vadhiyar
  IPDPS Workshops 2022.
  
  
• Equipping SBMs with RBMs: An interpretable approach for analysis of networks with covariates.
  Shubham Gupta, Gururaj K, Ambedkar Dukkipati and Rui M. Castro
  Journal of Complex Networks 10(2) 2022.
  
  
• Contradistinguisher: A Vapnik's Imperative to Unsupervised Domain Adaptation.
  Sourabh Balgi and Ambedkar Dukkipati
  IEEE Transactions on Pattern Analysis and Machine Intelligence ,44(9):4730-4747, 2022.
  [pdf]
  

2021

• Active^2 Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine Translation.
  Rishi Hazra, Parag Dutta, Shubham Gupta, Mohammed Abdul Qaathir and Ambedkar Dukkipati
  In Proceedings of NAACL: 2021.
  [arXiv]
  
  
• Neural Latent Space Model for Dynamic Networks and Temporal Knowledge Graphs.
  Tony Gracious, Shubham Gupta, Arun Kanthali, Rui M. Castro and Ambedkar Dukkipati
  In Proceedings of 35th AAAI Conference on Artificial Intelligence (AAAI): 2021.
  [pdf]
  
  
• SiameseGAN: A Generative model for Denoising of Spectral Domain Optical Coherence Tomography Images.
  Nilesh A. Kande, Rupali Dakhane, Ambedkar Dukkipati and Phaneendra K. Yalavarthy
  IEEE Transactions on Medical Imaging 40(1):180-192, 2021.
  [pdf]
  
  
• ActKnow: Active External Knowledge Infusion Learning for Question Answering in Low Data Regime
  Annervaz K. M, Pritam Kumar Nath and Ambedkar Dukkipati
  [arXiv]
  

2020

• Winning an Election: On Emergent Strategic Communication in Multi-Agent Networks
  Shubham Gupta and Ambedkar Dukkipati
  In AAMAS: 2020.
  
  
• Networked Multi-Agent Reinforcement Learning with Emergent Communication
  Shubham Gupta, Rishi Hazra and Ambedkar Dukkipati
  In AAMAS: 2020.
  
• A Regret bound for Nonstationary Multi-Armed Bandits with Fairness Constraints
  Ranga Shaarad Ayyagari and Ambedkar Dukkipati
  [arXiv]
  

2019

• CUDA : Contradistinguisher for Unsupervised Domain Adaptation
  Sourabh Balgi and Ambedkar Dukkipati
  In Proceedings of the IEEE International Conference on Data Mining (ICDM): 2019.
  [arXiv]
  
  
• Instance-based Inductive Deep Transfer Learning by Cross-Dataset Querying with Locality Sensitive Hashing.
  Somnath Basu Roy Chowdhury, Annervaz K. M and Ambedkar Dukkipati.
  In EMNLP Workshop on Deep Learning for Low-resource NLP : 2019.
  
  
• A generative model for dynamic networks with applications.
  Shubham Gupta, Gaurav Sharma and Ambedkar Dukkipati
  In Proceedings of 33rd AAAI Conference on Artificial Intelligence (AAAI): 2019.
  
  
• Skip Residual Pairwise Networks with Learnable Comparative Functions for Few-shot Learning.
  Akshay Mehrotra and Ambedkar Dukkipati
  In IEEE Winter Conference on Applications of Computer Vision (WACV): 2019.
  
  
• Learning to segment with image-level supervision.
  Gaurav Pandey and Ambedkar Dukkipati
  In IEEE Winter Conference on Applications of Computer Vision (WACV): 2019.
  [arXiv]

2018

• On Consistency of Compressive Spectral Clustering.
  Muni Srinivas Pydi and Ambedkar Dukkipati
  In Proceedings of IEEE International Symposium on Information Theory (ISIT): 2102-2106, 2018.
  [arXiv]
  
  
• Learning beyond datasets: Knowledge Graph Augmented Neural Networks for Natural language Processing.
  Annervaz K.M, Somnath Basu Roy Chowdhury and Ambedkar Dukkipati
  In Proceedings of NAACL HLT: 313-322, 2018.
  [pdf] [blog]
  
  
• On Grobner bases and Krull dimension of residue class rings of polynomial rings over integral domains.
  Maria Francis and Ambedkar Dukkipati
  Journal of Symbolic Computation 86:1-19, 2018.
  [Link] [arXiv]
  
  
• On Ideal Lattices, Grobner Bases and Generalized Hash Functions.
  Maria Francis and Ambedkar Dukkipati
  Journal of Algebra and its Applications 17 (06):1850112, 2018.
  [arXiv]

2017

• Unsupervised Feature Learning with Discriminative Encoder.
  Gaurav Pandey and Ambedkar Dukkipati
  In Proceedings of the IEEE International Conference on Data Mining (ICDM):367-376, 2017.
  
  
• Uniform Hypergraph Partitioning: Provable Tensor Methods and Sampling Techniques.
  Debarghya Ghoshdastidar and Ambedkar Dukkipati
  The Journal of Machine Learning Research 18(50):1-41, 2017.
  [arXiv]
  
  
• Attentive Recurrent Comparators.
  Pranav Shyam, Shubham Gupta and Ambedkar Dukkipati
  In Proceedings of the International Conference on Machine Learning (ICML):3173-3181, 2017.
  [bibtex] [arXiv] [blog]
  
  
• Variational methods for conditional multimodal deep learning.
  Gaurav Pandey and Ambedkar Dukkipati
  In Proceedings of the International Joint Conference on Neural Networks (IJCNN): 2017.
  [arXiv] [DEEPimagine]
  
  
• Consistency of Spectral Hypergraph Partitioning under Planted Partition Model.
  Debarghya Ghoshdastidar and Ambedkar Dukkipati
  The Annals of Statistics 45(1):289-315, 2017.
  [bibtex] [pdf] [arXiv]
  
  
• Primes of the form $x^2+d{y}^2$ with $x\equiv 0\left(\mathrm{mod}N\right)$ or $y\equiv 0\left(\mathrm{mod}N\right)$ .
  Ambedkar Dukkipati and Sushma Palimar
  Proc. Indian Acad. Sci. (Math. Sci.) 127(1): 35-43, 2017.

2016

• On Collapsed representations of hierarchical Completely Random Measures.
  Gaurav Pandey and Ambedkar Dukkipati
  In Proceedings of the 33rd International Conference on Machine Learning (ICML): 1605-1613, 2016.
  [pdf]
  
  
• Learning with Jensen-Tsallis kernels.
  Debarghya Ghoshdastidar, Ajay Adsul and Ambedkar Dukkipati
  IEEE Transactions on Neural Networks and Learning Systems 27(10): 2108-2119, 2016.
  [pdf]
  
  
• Mixture Modeling with Compact Support Distributions for Unsupervised Learning .
  Ambedkar Dukkipati, Debarghya Ghoshdastidar and Jinu Krishnan
  In Proceedings of the International Joint Conference on Neural Networks (IJCNN): 2706-2713, 2016.
  [pdf]
  

2015

• A Provable Generalized Tensor Spectral Method for Uniform Hypergraph Partitioning.
  Debarghya Ghoshdastidar and Ambedkar Dukkipati
  In Proceedings of the 32nd International Conference on Machine Learning (ICML), 2015.
  [pdf]
  
  
• A faster algorithm for testing polynomial representability of functions over finite integer rings.
  Ashwin Guha and Ambedkar Dukkipati
  Theoretical Computer Science 579:88–99, 2015.
  [bibtex] [arXiv]
  
  
• An algorithmic characterization of polynomial functions over Z_{p^n}.
  Ashwin Guha and Ambedkar Dukkipati
  Algorithmica 71(1):201-218, 2015.
  [bibtex] [arXiv]
  
  
• Spectral Clustering using Multilinear SVD: Analysis, Approximations and Applications.
  Debarghya Ghoshdastidar and Ambedkar Dukkipati
  In Proceedings of 29th AAAI Conference on Artificial Intelligence (AAAI): 2610-2616, 2015.
  [pdf]

2014

• Consistency of Spectral Partitioning of Uniform Hypergraphs under Planted Partition Model.
  Debarghya Ghoshdastidar and Ambedkar Dukkipati
  In Advances in Neural Information Processing Systems (NIPS): 397-405, 2014.
  [pdf]
  
  
• Newton based Stochastic Optimization using q-Gaussian Smoothed Functional Algorithms.
  Debarghya Ghoshdastidar, Ambedkar Dukkipati and Shalabh Bhatnagar
  Automatica 50(10):2606–2614, 2014.
  
  
• Smoothed functional algorithms for stochastic optimization using q-Gaussian distributions.
  Debarghya Ghoshdastidar, Ambedkar Dukkipati and Shalabh Bhatnagar
  ACM Transactions on Modeling and Computer Simulation 24(3):1-26, 2014.
  
  
• Learning by stretching deep networks.
  Gaurav Pandey and Ambedkar Dukkipati
  In Proceedings of the 31st International Conference on Machine Learning (ICML): 1719-1727, 2014.
  [pdf]
  
  
• Spectral clustering with Jensen-type kernels and their multi-point extensions.
  Debarghya Ghoshdastidar, Ambedkar Dukkipati, Ajay P. Adsul and Aparna S. Vijayan
  In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR): 1472-1477, 2014.
  [pdf]
  
  
• To go deep or wide in learning?
  Gaurav Pandey and Ambedkar Dukkipati
  In Proceedings of Seventeenth International Conference on Artificial Intelligence and Statistics (AISTATS): 724-732, 2014.
  [pdf]
  
  
• Reduced Grobner bases and Macaulay-Buchberger basis theorem over Noetherian rings.
  Maria Francis and Ambedkar Dukkipati
  Journal of Symbolic Computation 65:1-14, 2014.
  [bibtex] [Link] [arXiv]
  

2013

• Generative maximum entropy learning for multiclass classification.
  Ambedkar Dukkipati, Gaurav Pandey, Debarghya Ghoshdastidar, Paramita Koley and D. M. V. S. Sriram
  In Proceedings of IEEE International Conference on Data Mining (ICDM), pp. 141-150, IEEE press, 2013. (Regular Paper)
  [bibtex] [pdf]
  
  
• Minimum description length principle for maximum entropy model selection.
  Gaurav Pandey and Ambedkar Dukkipati
  In Proceedings of IEEE International Symposium on Information Theory (ISIT), pp. 1521-1525, IEEE press, 2013.
  [bibtex] [pdf]
  
  
• On power law kernels, corresponding reproducing kernel Hilbert space and applications.
  Debarghya Ghoshdastidar and Ambedkar Dukkipati
  In Proceedings of 27th AAAI Conference on Artificial Intelligence (AAAI) 2013.
  [bibtex] [pdf]
  

2012

• Complexity of Gröbner basis detection and border basis detection.
  Prabhanjan V. Ananth and Ambedkar Dukkipati
  Theoretical Computer Science 459: 1-15, 2012.
  [bibtex] [Link]
  
  
• On maximum entropy and minimum KL-divergence optimization by Gröbner basis methods.
  Ambedkar Dukkipati
  Applied Mathematics and Computation 218: 11674-11687, 2012.
  [bibtex]
  
  
• An algebraic characterization of rainbow connectivity.
  Prabhanjan V. Ananth and Ambedkar Dukkipati
  V. P. Gerdt et al. (Eds.) In Proceedings of International Workshop on Computer Algebra in Scientific Computing (CASC): 12-21, Springer Lecture Notes in Computer Science, 2012.
  [bibtex]
  
  
• q-Gaussian based smoothed functional algorithms for stochastic optimization.
  Debarghya Ghoshdastidar, Ambedkar Dukkipati and Shalabh Bhatnagar
  In Proceedings of IEEE International Symposium on Information Theory (ISIT): 1059-1063, IEEE press, 2012.
  
  
• A two stage selective averaging LDPC decoding.
  Dinesh Kumar and Ambedkar Dukkipati
  In Proceedings of IEEE International Symposium on Information Theory (ISIT), pp. 2866-2870, IEEE press, 2012.
  

2011

• Border basis detection is NP-complete.
  Prabhanjan V. Ananath and Ambedkar Dukkipati
  In Proceedings of ACM 36th International Symposium on Symbolic and Algebraic Computation (ISSAC): 11-18, ACM 2011
  [bibtex] [arXiv] [Link]
  

2010

• An algebraic implicitization and specialization of minimum KL-divergence models.
  Ambedkar Dukkipati and Joel G. Manathara
  V. P. Gerdt et al. (Eds.) In Proceedings of International Workshop on Computer Algebra in Scientific Computing (CASC): 85-96, Springer Lecture Notes in Computer Science, 2010.
  
  
• On Kolmogorov-Nagumo averages and nonextensive entropy.
  Ambedkar Dukkipati
  In Proceedings of International Symposium on Information Theory and its Applications(ISITA), pp. 446-451 IEEE press 2010.
  
  
• Maximum entropy model based classification with feature selection.
  Ambedkar Dukkipati, Abhay Kumar Yadav and M. Narasimha Murty
  In Proceedings of IEEE International Conference on Pattern Recognition (ICPR), pp. 565-568, IEEE press, 2010.
  

2009

• Embedding maximum entropy models in algebraic varieties by Grobner bases methods.
  Ambedkar Dukkipati
  In Proceedings of IEEE International Symposium on Information Theory (ISIT), pp.1904-1908, IEEE press, 2009.
  [bibtex]

2007

• On measure-theoretic aspects of nonextensive entropy functionals and corresponding maximum entropy prescriptions.
  Ambedkar Dukkipati, Shalabh Bhatnagar and M. Narasimha Murty
  Physica A: Statistical Mechanics and its Applications, 384:124-138, 2007. [Link]
  
  
• Gelfand-Yaglom-Perez theorem for generalized relative entropy functionals.
  Ambedkar Dukkipati, Shalabh Bhatnagar and M. Narasimha Murty
  Information Sciences, 177:5707-5714, 2007.
  

2006

• Nonextensive triangle equality and other properties of Tsallis relative-entropy minimization.
  Ambedkar Dukkipati, M. Narasimha Murty and Shalabh Bhatnagar
  Physica A: Statistical Mechanics and its Applications, Vol. 361, pp 124-138, 2006.
  

2005

• Information theoretic justification of Boltzmann selection and its generalization to Tsallis case.
  Ambedkar Dukkipati, M. Narasimha Murty and Shalabh Bhatnagar
  In Proceedings of IEEE Congress on Evolutionary Computation (CEC) . Vol. 2, pp. 1667-1674, IEEE press, 2005. pdf
  
  
• Properties of Kullback-Leibler cross-entropy minimization in nonextensive framework.
  Ambedkar Dukkipati, M. Narasimha Murty and Shalabh Bhatnagar
  In Proceedings of IEEE International Symposium on Information Theory (ISIT), pp. 2374--2378, IEEE press, 2005.
  
Back to top.

Technical Reports and Unpublished Papers

• CoviHawkes: Temporal Point Process and Deep Learning based Covid-19 forecasting for India. (by Ambedkar Dukkipati, Tony Gracious and Shuham Gupta) 2021. arXiv
  
  
• Tropical algebraic approach to consensus over networks. (by Joel G. Manathara, Ambedkar Dukkipati and Debasish Ghose) 2011. arXiv
  
  
• On parametric and implicit algebraic descriptions of maximum entropy models. (by Ambedkar Dukkipati)
  EURANDOM report 2008-038, 2008.
  
Back to top.

Research Group

• Statistics and Machine Learning